---
type: "firecrawl-provider"
description: "ElevenLabs developer docs, pricing and help center from elevenlabs.io and help.elevenlabs.io: search and list the docs, read any docs page or one section as clean Markdown, structured API endpoint references (method, URL, parameters, responses), the model list with limits and languages, the changelog, plan, API and agents pricing, blog posts, and help center article search and full articles. Public agent-facing sources only (llms.txt, Markdown twins, schema.org data, the public Zendesk Help Center API); no API key or login."
use_when: "ElevenLabs developer docs, pricing and help center from elevenlabs.io and help.elevenlabs.io: search and list the docs, read any docs page or one section as clean Markdown, structured API endpoint references (method, URL, parameters, responses), the model list with limits and languages, the changelog, plan, API and agents pricing, blog posts, and help center article search and full articles. Public agent-facing sources only (llms.txt, Markdown twins, schema.org data, the public Zendesk Help Center API); no API key or login."
categories: "AI models"
capabilities: 12
credits_per_call: 5
---
# ElevenLabs on Firecrawl Alexandria

ElevenLabs developer docs, pricing and help center from elevenlabs.io and help.elevenlabs.io: search and list the docs, read any docs page or one section as clean Markdown, structured API endpoint references (method, URL, parameters, responses), the model list with limits and languages, the changelog, plan, API and agents pricing, blog posts, and help center article search and full articles. Public agent-facing sources only (llms.txt, Markdown twins, schema.org data, the public Zendesk Help Center API); no API key or login.

- Categories: AI models
- Category index: [AI models category](https://firecrawl.dev/alexandria/agents/categories/ai-models)
- Provider key: `elevenlabs-io`
- Access: Firecrawl credits
- Cost: 5 credits per call

## More

- [Human guide](https://firecrawl.dev/app/alexandria/elevenlabs-io)
- [OpenAPI spec](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/openapi.json)

## Capabilities

- [Get api endpoint](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/get_api_endpoint): One ElevenLabs API endpoint reference from its docs page (elevenlabs.io/docs/api-reference/...): method, endpoint URL and API path, content type, description, regional servers, every parameter by location (path, query, header, body) with type, required, nullable, deprecated, default, description and allowed values, the body type, responses with their fields, errors and the example request body. WebSocket pages report kind `websocket` with method and path only. Accepts a docs path or URL; a page that is not an endpoint reference is `not_found`.
- [Get blog post](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/get_blog_post): One ElevenLabs blog post (elevenlabs.io/blog/{slug}): title, description, category, authors, published and modified times from its schema.org Article data, and the article body converted to Markdown (`max_chars› truncates). Accepts a slug or post URL; a page that is not a post is `not_found›.
- [Get help article](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/get_help_article): One ElevenLabs help center article (help.elevenlabs.io) from the public Zendesk Help Center API: title, URL, locale, section and category, labels, created, updated and edited times, votes, and the body converted to Markdown (`max_chars` truncates). Accepts the numeric article id or an article URL; unknown ids are `not_found`.
- [Get model](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/get_model): One ElevenLabs model by id from the official models page: the same fields as list_models plus the Markdown of the page section that describes the model (use cases, supported languages, considerations), `max_chars› truncates. `content› is null when the page has no section for that model. Unknown ids are `not_found›.
- [Get page](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/get_page): One ElevenLabs developer docs page as clean Markdown from its official `.md` twin (elevenlabs.io/docs/{path}.md): title, description, URL, an outline of every heading (level, text, anchor) and the content. Pass `section` (heading text or anchor) for only that heading's subtree; `max_chars` truncates. Accepts a docs path or an elevenlabs.io/docs URL (an anchor selects that section). Unknown pages and sections are `not_found`.
- [Get pricing](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/get_pricing): ElevenLabs pricing from every public pricing tab's schema.org FAQ data, no clicks needed: `plans› (elevenlabs.io/pricing) gives each plan's monthly USD price, monthly credits, seats, notes and annual-billing monthly equivalent plus the credits FAQ; `api› (elevenlabs.io/pricing/api) gives per-product API rates in USD; `agents› (elevenlabs.io/pricing/agents) gives ElevenAgents included call minutes and concurrent calls per plan plus overage, burst and telephony terms. `all› (default) returns the three tabs.
- [List blog posts](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/list_blog_posts): The latest ElevenLabs blog posts (elevenlabs.io/blog) from the official RSS feed (about 50 newest): title, URL, slug, ISO publish date, description, category (Product, Resources, Company, Customer Stories, Research) and authors. Filter by `category› and text `q›; page with `limit›/`offset›.
- [List changelog](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/list_changelog): The ElevenLabs product and API changelog (elevenlabs.io/docs/changelog) as dated entries newest first: ISO date, heading anchor and URL, topics (the entry's subheadings, e.g. Eleven Realtime, SDK releases), and the entry's Markdown including new and updated endpoints, cut at `max_chars_per_entry›. Filter with `since› (YYYY-MM-DD) and a text `q›; page with `limit›/`offset›.
- [List models](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/list_models): Every ElevenLabs API model from the official models page (elevenlabs.io/docs/overview/models): model id, description, languages (text plus language codes when listed), latency in ms when stated, character limit and approximate audio duration from the character limits table, status (current or deprecated), replacement for deprecated models and the docs section that describes it. Filter with `q›; `include_deprecated› defaults to true.
- [List pages](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/list_pages): List the pages of the ElevenLabs developer docs from the public llms.txt index: title, docs path, URL, Markdown URL, description and navigation breadcrumb, for guides (`docs`) and API reference endpoints (`api`). Filter by section and a case-insensitive substring `q`; page with `limit` and `offset`.
- [Search docs](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/search_docs): Search the official ElevenLabs developer docs (elevenlabs.io/docs) by keywords: guides, product pages and every API reference endpoint, ranked by how many query terms each page's title, path, navigation group and description contain. Returns page titles, docs paths, URLs, Markdown URLs, descriptions and navigation breadcrumbs. Built on the docs' public llms.txt index.
- [Search help articles](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/search_help_articles): Search the ElevenLabs help center (help.elevenlabs.io) through its public Zendesk Help Center API: article id, title, URL, section id, highlighted snippet as plain text, labels, created and updated times and vote sum, with the total match count. Page with `page`; `next_page` continues.

## 1. Choose this provider when

ElevenLabs developer docs, pricing and help center from elevenlabs.io and help.elevenlabs.io: search and list the docs, read any docs page or one section as clean Markdown, structured API endpoint references (method, URL, parameters, responses), the model list with limits and languages, the changelog, plan, API and agents pricing, blog posts, and help center article search and full articles. Public agent-facing sources only (llms.txt, Markdown twins, schema.org data, the public Zendesk Help Center API); no API key or login.

## 2. Minimal request

Call `POST https://api.firecrawl.dev/v2/scrape` with `{ alexandria: { provider, capability, options } }`. For a batch, send `{ alexandria: [...] }` with up to 10 calls.

```json
{
  "provider": "elevenlabs-io",
  "capability": "developer-docs/get_api_endpoint",
  "options": {
    "path": "api-reference/text-to-speech/convert"
  }
}
```

## 3. Add provider options

Use only the options needed for the task:

- `path` (string): API reference docs path, e.g. `api-reference/text-to-speech/convert` (from search_docs or list_pages). Example: `api-reference/text-to-speech/convert`
- `url` (string): Alternatively the reference URL, e.g. https://elevenlabs.io/docs/api-reference/text-to-speech/convert. Pattern: ^https?://. Example: `<url>`

## 4. Request through your preferred interface

### JavaScript

```javascript
const result = await firecrawl.scrape({
  alexandria: {
    provider: "elevenlabs-io",
    capability: "developer-docs/get_api_endpoint",
    options: {
      path: "api-reference/text-to-speech/convert",
    },
  },
});
```

### Python

```python
result = firecrawl.scrape_alexandria({
  "provider": "elevenlabs-io",
  "capability": "developer-docs/get_api_endpoint",
  "options": {
    "path": "api-reference/text-to-speech/convert"
  }
})
```

### cURL

```sh
curl https://api.firecrawl.dev/v2/scrape \
  -H "Authorization: Bearer $FIRECRAWL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "alexandria": {
    "provider": "elevenlabs-io",
    "capability": "developer-docs/get_api_endpoint",
    "options": {
      "path": "api-reference/text-to-speech/convert"
    }
  }
}'
```

### CLI

```sh
firecrawl scrape 'elevenlabs-io/developer-docs/get_api_endpoint' \
  --options '{"path":"api-reference/text-to-speech/convert"}'
```


### MCP

Call the FCX MCP retrieve tool with this object:

```json
{
  "provider": "elevenlabs-io",
  "capability": "developer-docs/get_api_endpoint",
  "options": {
    "path": "api-reference/text-to-speech/convert"
  }
}
```

Ask for only the returned fields needed by the task.

## 5. Full request shape

```json
{
  "provider": "elevenlabs-io",
  "capability": "developer-docs/get_api_endpoint",
  "options": {
    "path": "api-reference/text-to-speech/convert"
  }
}
```

## 6. Response data

The response includes `success`, `provider`, `capability`, `creditsCost` and `data`. This example shows the provider payload in `data`:

```json
{
  "api_path": "/v1/text-to-speech/{voice_id}",
  "body_type": "Body_text_to_speech_full",
  "content_type": "application/json",
  "description": "Converts text into speech using a voice of your choice and returns audio.",
  "endpoint": "https://api.elevenlabs.io/v1/text-to-speech/{voice_id}",
  "errors": [
    {
      "description": "Validation Error",
      "name": "Unprocessable Entity Error",
      "status": "422"
    }
  ],
  "example_request": "{\n  \"text\": \"The first move is what sets everything in motion.\",\n  \"model_id\": \"eleven_multilingual_v2\"\n}",
  "kind": "http",
  "markdown_url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert.md",
  "method": "POST",
  "observed_at_ms": 1792693978959,
  "parameters": [
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "ID of the voice to be used. Use the [Get voices](/docs/api-reference/voices/search) endpoint list all the available voices.",
      "location": "path",
      "name": "voice_id",
      "nullable": false,
      "required": true,
      "type": "string"
    },
    {
      "allowed_values": null,
      "default": "true",
      "deprecated": false,
      "description": "When enable_logging is set to false zero retention mode will be used for the request. This will mean history features are unavailable for this request, including request stitching. Zero retention mode may only be used by enterprise customers.",
      "location": "query",
      "name": "enable_logging",
      "nullable": false,
      "required": false,
      "type": "boolean"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": true,
      "description": "You can turn on latency optimizations at some cost of quality. The best possible final latency varies by model. Possible values: 0 - default mode (no latency optimizations) 1 - normal latency optimizations (about 50% of possible latency improvement of option 3) 2 - strong latency optimizations (about 75% of possible latency improvement of option 3) 3 - max latency optimizations 4 - max latency optimizations, but also with text normalizer turned off for even more latency savings (best latency, but can mispronounce eg numbers and dates). Defaults to None.",
      "location": "query",
      "name": "optimize_streaming_latency",
      "nullable": true,
      "required": false,
      "type": "integer"
    },
    {
      "allowed_values": [
        "alaw_8000",
        "mp3_22050_32",
        "mp3_24000_48",
        "mp3_44100_128",
        "mp3_44100_192",
        "mp3_44100_32",
        "mp3_44100_64",
        "mp3_44100_96",
        "opus_48000_128",
        "opus_48000_192",
        "opus_48000_32",
        "opus_48000_64",
        "opus_48000_96",
        "pcm_16000",
        "pcm_22050",
        "pcm_24000",
        "pcm_32000",
        "pcm_44100",
        "pcm_48000",
        "pcm_8000",
        "ulaw_8000",
        "wav_16000",
        "wav_22050",
        "wav_24000",
        "wav_32000",
        "wav_44100",
        "wav_48000",
        "wav_8000"
      ],
      "default": "mp3_44100_128",
      "deprecated": false,
      "description": "Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM and WAV formats with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.",
      "location": "query",
      "name": "output_format",
      "nullable": false,
      "required": false,
      "type": "enum"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "The text that will get converted into speech.",
      "location": "body",
      "name": "text",
      "nullable": false,
      "required": true,
      "type": "string"
    },
    {
      "allowed_values": null,
      "default": "eleven_multilingual_v2",
      "deprecated": false,
      "description": "Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property.",
      "location": "body",
      "name": "model_id",
      "nullable": false,
      "required": false,
      "type": "string"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "Language code (ISO 639-1) used to enforce a language for the model and text normalization. If the model does not support the provided language code, it will be ignored. This parameter is not supported for multilingual_v2 models.",
      "location": "body",
      "name": "language_code",
      "nullable": true,
      "required": false,
      "type": "string"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "Voice settings overriding stored settings for the given voice. They are applied only on the given request.",
      "location": "body",
      "name": "voice_settings",
      "nullable": true,
      "required": false,
      "type": "VoiceSettingsResponseModel"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "A list of pronunciation dictionary locators (id, version_id) to be applied to the text. They will be applied in order. You may have up to 3 locators per request",
      "location": "body",
      "name": "pronunciation_dictionary_locators",
      "nullable": true,
      "required": false,
      "type": "list of PronunciationDictionaryVersionLocatorRequestModel"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be integer between 0 and 4294967295.",
      "location": "body",
      "name": "seed",
      "nullable": true,
      "required": false,
      "type": "integer"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.",
      "location": "body",
      "name": "previous_text",
      "nullable": true,
      "required": false,
      "type": "string"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.",
      "location": "body",
      "name": "next_text",
      "nullable": true,
      "required": false,
      "type": "string"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "A list of request_id of the samples that were generated before this generation. Can be used to improve the speech's continuity when splitting up a large task into multiple requests. The results will be best when the same model is used across the generations. In case both previous_text and previous_request_ids is send, previous_text will be ignored. A maximum of 3 request_ids can be send.",
      "location": "body",
      "name": "previous_request_ids",
      "nullable": true,
      "required": false,
      "type": "list of string"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "A list of request_id of the samples that come after this generation. next_request_ids is especially useful for maintaining the speech's continuity when regenerating a sample that has had some audio quality issues. For example, if you have generated 3 speech clips, and you want to improve clip 2, passing the request id of clip 3 as a next_request_id (and that of clip 1 as a previous_request_id) will help maintain natural flow in the combined speech. The results will be best when the same model is used across the generations. In case both next_text and next_request_ids is send, next_text will be ignored. A maximum of 3 request_ids can be send.",
      "location": "body",
      "name": "next_request_ids",
      "nullable": true,
      "required": false,
      "type": "list of string"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "Whether to use the IVC version of a professional voice. This may improve expressiveness and reduce latency.",
      "location": "body",
      "name": "use_pvc_as_ivc",
      "nullable": true,
      "required": false,
      "type": "boolean"
    },
    {
      "allowed_values": [
        "auto",
        "on",
        "off"
      ],
      "default": "auto",
      "deprecated": false,
      "description": "This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped.",
      "location": "body",
      "name": "apply_text_normalization",
      "nullable": false,
      "required": false,
      "type": "enum"
    },
    {
      "allowed_values": null,
      "default": "false",
      "deprecated": false,
      "description": "This parameter controls language text normalization. This helps with proper pronunciation of text in some supported languages. WARNING: This parameter can heavily increase the latency of the request. Currently only supported for Japanese.",
      "location": "body",
      "name": "apply_language_text_normalization",
      "nullable": false,
      "required": false,
      "type": "boolean"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "Audio effects applied to the generated audio. Unknown IDs return 404 with `param` naming the field. Reverb (`environment_id` with `send_level` above 0) and a non-zero `pan` produce stereo audio and are rejected with 400 for `ulaw_*`, `alaw_*`, and `pcm_*` output formats. Effects don't change the cost of the request.",
      "location": "body",
      "name": "audio_effects",
      "nullable": true,
      "required": false,
      "type": "EffectsSpec-Input"
    }
  ],
  "path": "api-reference/text-to-speech/convert",
  "responses": [
    {
      "description": "The generated audio file",
      "fields": [],
      "status": "200"
    }
  ],
  "servers": [
    {
      "label": "Production, default",
      "url": "https://api.elevenlabs.io"
    },
    {
      "label": "Production US",
      "url": "https://api.us.elevenlabs.io"
    },
    {
      "label": "Production EU",
      "url": "https://api.eu.residency.elevenlabs.io"
    },
    {
      "label": "Production India",
      "url": "https://api.in.residency.elevenlabs.io"
    },
    {
      "label": "Production Singapore",
      "url": "https://api.sg.residency.elevenlabs.io"
    }
  ],
  "title": "Create speech",
  "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert"
}
```

## API reference-derived contract

The following capability contract is generated from the same normalized Alexandria API reference exposed in the API spec.

### Get api endpoint

- Capability: `developer-docs/get_api_endpoint`
- Description: One ElevenLabs API endpoint reference from its docs page (elevenlabs.io/docs/api-reference/...): method, endpoint URL and API path, content type, description, regional servers, every parameter by location (path, query, header, body) with type, required, nullable, deprecated, default, description and allowed values, the body type, responses with their fields, errors and the example request body. WebSocket pages report kind `websocket` with method and path only. Accepts a docs path or URL; a page that is not an endpoint reference is `not_found`.
- Instructions: To build or check a call to the ElevenLabs API, e.g. the parameters and output formats of Create speech.
- Cost: 5 credits per call
- Capability file: [Get api endpoint](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/get_api_endpoint)

Accepted options:
- `path` (string): API reference docs path, e.g. `api-reference/text-to-speech/convert` (from search_docs or list_pages). Example: `api-reference/text-to-speech/convert`
- `url` (string): Alternatively the reference URL, e.g. https://elevenlabs.io/docs/api-reference/text-to-speech/convert. Pattern: ^https?://. Example: `<url>`

Response schema example:
```json
{
  "api_path": "/v1/text-to-speech/{voice_id}",
  "body_type": "Body_text_to_speech_full",
  "content_type": "application/json",
  "description": "Converts text into speech using a voice of your choice and returns audio.",
  "endpoint": "https://api.elevenlabs.io/v1/text-to-speech/{voice_id}",
  "errors": [
    {
      "description": "Validation Error",
      "name": "Unprocessable Entity Error",
      "status": "422"
    }
  ],
  "example_request": "{\n  \"text\": \"The first move is what sets everything in motion.\",\n  \"model_id\": \"eleven_multilingual_v2\"\n}",
  "kind": "http",
  "markdown_url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert.md",
  "method": "POST",
  "observed_at_ms": 1792693978959,
  "parameters": [
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "ID of the voice to be used. Use the [Get voices](/docs/api-reference/voices/search) endpoint list all the available voices.",
      "location": "path",
      "name": "voice_id",
      "nullable": false,
      "required": true,
      "type": "string"
    },
    {
      "allowed_values": null,
      "default": "true",
      "deprecated": false,
      "description": "When enable_logging is set to false zero retention mode will be used for the request. This will mean history features are unavailable for this request, including request stitching. Zero retention mode may only be used by enterprise customers.",
      "location": "query",
      "name": "enable_logging",
      "nullable": false,
      "required": false,
      "type": "boolean"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": true,
      "description": "You can turn on latency optimizations at some cost of quality. The best possible final latency varies by model. Possible values: 0 - default mode (no latency optimizations) 1 - normal latency optimizations (about 50% of possible latency improvement of option 3) 2 - strong latency optimizations (about 75% of possible latency improvement of option 3) 3 - max latency optimizations 4 - max latency optimizations, but also with text normalizer turned off for even more latency savings (best latency, but can mispronounce eg numbers and dates). Defaults to None.",
      "location": "query",
      "name": "optimize_streaming_latency",
      "nullable": true,
      "required": false,
      "type": "integer"
    },
    {
      "allowed_values": [
        "alaw_8000",
        "mp3_22050_32",
        "mp3_24000_48",
        "mp3_44100_128",
        "mp3_44100_192",
        "mp3_44100_32",
        "mp3_44100_64",
        "mp3_44100_96",
        "opus_48000_128",
        "opus_48000_192",
        "opus_48000_32",
        "opus_48000_64",
        "opus_48000_96",
        "pcm_16000",
        "pcm_22050",
        "pcm_24000",
        "pcm_32000",
        "pcm_44100",
        "pcm_48000",
        "pcm_8000",
        "ulaw_8000",
        "wav_16000",
        "wav_22050",
        "wav_24000",
        "wav_32000",
        "wav_44100",
        "wav_48000",
        "wav_8000"
      ],
      "default": "mp3_44100_128",
      "deprecated": false,
      "description": "Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM and WAV formats with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.",
      "location": "query",
      "name": "output_format",
      "nullable": false,
      "required": false,
      "type": "enum"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "The text that will get converted into speech.",
      "location": "body",
      "name": "text",
      "nullable": false,
      "required": true,
      "type": "string"
    },
    {
      "allowed_values": null,
      "default": "eleven_multilingual_v2",
      "deprecated": false,
      "description": "Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property.",
      "location": "body",
      "name": "model_id",
      "nullable": false,
      "required": false,
      "type": "string"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "Language code (ISO 639-1) used to enforce a language for the model and text normalization. If the model does not support the provided language code, it will be ignored. This parameter is not supported for multilingual_v2 models.",
      "location": "body",
      "name": "language_code",
      "nullable": true,
      "required": false,
      "type": "string"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "Voice settings overriding stored settings for the given voice. They are applied only on the given request.",
      "location": "body",
      "name": "voice_settings",
      "nullable": true,
      "required": false,
      "type": "VoiceSettingsResponseModel"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "A list of pronunciation dictionary locators (id, version_id) to be applied to the text. They will be applied in order. You may have up to 3 locators per request",
      "location": "body",
      "name": "pronunciation_dictionary_locators",
      "nullable": true,
      "required": false,
      "type": "list of PronunciationDictionaryVersionLocatorRequestModel"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be integer between 0 and 4294967295.",
      "location": "body",
      "name": "seed",
      "nullable": true,
      "required": false,
      "type": "integer"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.",
      "location": "body",
      "name": "previous_text",
      "nullable": true,
      "required": false,
      "type": "string"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.",
      "location": "body",
      "name": "next_text",
      "nullable": true,
      "required": false,
      "type": "string"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "A list of request_id of the samples that were generated before this generation. Can be used to improve the speech's continuity when splitting up a large task into multiple requests. The results will be best when the same model is used across the generations. In case both previous_text and previous_request_ids is send, previous_text will be ignored. A maximum of 3 request_ids can be send.",
      "location": "body",
      "name": "previous_request_ids",
      "nullable": true,
      "required": false,
      "type": "list of string"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "A list of request_id of the samples that come after this generation. next_request_ids is especially useful for maintaining the speech's continuity when regenerating a sample that has had some audio quality issues. For example, if you have generated 3 speech clips, and you want to improve clip 2, passing the request id of clip 3 as a next_request_id (and that of clip 1 as a previous_request_id) will help maintain natural flow in the combined speech. The results will be best when the same model is used across the generations. In case both next_text and next_request_ids is send, next_text will be ignored. A maximum of 3 request_ids can be send.",
      "location": "body",
      "name": "next_request_ids",
      "nullable": true,
      "required": false,
      "type": "list of string"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "Whether to use the IVC version of a professional voice. This may improve expressiveness and reduce latency.",
      "location": "body",
      "name": "use_pvc_as_ivc",
      "nullable": true,
      "required": false,
      "type": "boolean"
    },
    {
      "allowed_values": [
        "auto",
        "on",
        "off"
      ],
      "default": "auto",
      "deprecated": false,
      "description": "This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped.",
      "location": "body",
      "name": "apply_text_normalization",
      "nullable": false,
      "required": false,
      "type": "enum"
    },
    {
      "allowed_values": null,
      "default": "false",
      "deprecated": false,
      "description": "This parameter controls language text normalization. This helps with proper pronunciation of text in some supported languages. WARNING: This parameter can heavily increase the latency of the request. Currently only supported for Japanese.",
      "location": "body",
      "name": "apply_language_text_normalization",
      "nullable": false,
      "required": false,
      "type": "boolean"
    },
    {
      "allowed_values": null,
      "default": null,
      "deprecated": false,
      "description": "Audio effects applied to the generated audio. Unknown IDs return 404 with `param` naming the field. Reverb (`environment_id` with `send_level` above 0) and a non-zero `pan` produce stereo audio and are rejected with 400 for `ulaw_*`, `alaw_*`, and `pcm_*` output formats. Effects don't change the cost of the request.",
      "location": "body",
      "name": "audio_effects",
      "nullable": true,
      "required": false,
      "type": "EffectsSpec-Input"
    }
  ],
  "path": "api-reference/text-to-speech/convert",
  "responses": [
    {
      "description": "The generated audio file",
      "fields": [],
      "status": "200"
    }
  ],
  "servers": [
    {
      "label": "Production, default",
      "url": "https://api.elevenlabs.io"
    },
    {
      "label": "Production US",
      "url": "https://api.us.elevenlabs.io"
    },
    {
      "label": "Production EU",
      "url": "https://api.eu.residency.elevenlabs.io"
    },
    {
      "label": "Production India",
      "url": "https://api.in.residency.elevenlabs.io"
    },
    {
      "label": "Production Singapore",
      "url": "https://api.sg.residency.elevenlabs.io"
    }
  ],
  "title": "Create speech",
  "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert"
}
```

### Get blog post

- Capability: `developer-docs/get_blog_post`
- Description: One ElevenLabs blog post (elevenlabs.io/blog/{slug}): title, description, category, authors, published and modified times from its schema.org Article data, and the article body converted to Markdown (`max_chars› truncates). Accepts a slug or post URL; a page that is not a post is `not_found›.
- Instructions: To read an ElevenLabs announcement or guide in full, e.g. a model launch post.
- Cost: 5 credits per call
- Capability file: [Get blog post](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/get_blog_post)

Accepted options:
- `max_chars` (number): Truncate `content›; whole text when omitted. Example: `200`
- `slug` (string): Post slug, e.g. `voice-conversion›. Example: `<slug>`
- `url` (string): Alternatively a post URL, e.g. https://elevenlabs.io/blog/voice-conversion. Pattern: ^https?://. Example: `<url>`

Response schema example:
```json
{
  "authors": [
    "ElevenLabs"
  ],
  "category": "research",
  "chars": 8206,
  "content": "### What's voice conversion?\n\nVoice conversion lets you transform one person's voice into another’s. It uses a process called [voice cloning](https://elevenlabs.io/blog/what-is-voice-cloning) to encode the target voice - ie, the voice we convert to - and generate the same message spoken in a way which matches the target speaker’s identity but preserves the original intonation.\n\n### Uses\n\nHigh quality voice conversion and voice cloning technology have the potential to revolutionise the way content is produced, delivered and interacted with across a range of industries. They promise to optimise production time and costs and to provide those who share their voices to train conversion algorithms with ways to earn passive fees.\n\n- In filmmaking actors could share their voice databases with producers to create audio tracks without the need to travel to set or studio;\n- misspoken lines could be re-recorded much more effectively in post production;\n- the technology can also be used to faithfully reproduce the voices of historical figures in fictional scenarios or to bring deceased actors back to life;\n- video game development will find the technology useful to a similar extent: correcting utterances or simply experimenting could be done on the spot and without the actor physically present for recording;\n- in medicine patients who lost the ability to speak, for example as a result of throat cancer treatment, can be given the chance to communicate again in their own voice;\n- virtual as",
  "description": "What's voice conversion? Voice conversion lets you transform one person's voice into another’s. Discover how with ElevenLabs voice cloning",
  "modified": "2026-09-10T18:25:28.015Z",
  "observed_at_ms": 1792695902051,
  "published": "2022-09-06T10:58:06.000Z",
  "slug": "voice-conversion",
  "title": "Voice Conversion",
  "truncated": true,
  "url": "https://elevenlabs.io/blog/voice-conversion"
}
```

### Get help article

- Capability: `developer-docs/get_help_article`
- Description: One ElevenLabs help center article (help.elevenlabs.io) from the public Zendesk Help Center API: title, URL, locale, section and category, labels, created, updated and edited times, votes, and the body converted to Markdown (`max_chars` truncates). Accepts the numeric article id or an article URL; unknown ids are `not_found`.
- Instructions: To read a help center answer in full, e.g. the supported languages list.
- Cost: 5 credits per call
- Capability file: [Get help article](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/get_help_article)

Accepted options:
- `id` (number): Article id, e.g. 13313366263441. Example: `10`
- `max_chars` (number): Truncate `content`; whole text when omitted. Example: `200`
- `url` (string): Alternatively an article URL, e.g. https://help.elevenlabs.io/hc/en-us/articles/13313366263441. Pattern: ^https?://. Example: `<url>`

Response schema example:
```json
{
  "category": {
    "id": 23811324705809,
    "name": "Other",
    "url": "https://help.elevenlabs.io/hc/en-us/categories/23811324705809-Other"
  },
  "chars": 3555,
  "content": "**Eleven v3 -** our latest and most advanced speech synthesis model. It is a state-of-the-art model that produces natural, life-like speech with high emotional range and contextual understanding across multiple languages.\n\n**Eleven v3 Conversational** - our most emotionally intelligent, context-aware Text to Speech model, built on Eleven v3 and optimized for real-time dialogue.\n\nEleven v3 supports 74 languages:\n\n- **AFR** Afrikaans\n- **ARA** Arabic\n- **HYE** Armenian\n- **ASM** Assamese\n- **AZE** Azerbaijani\n- **BEL** Belarusian\n- **BEN** Bengali\n- **BOS** Bosnian\n- **BUL** Bulgarian\n- **CAT** Catalan\n- **CEB** Cebuano\n- **NYA** Chichewa\n- **HRV** Croatian\n- **CES** Czech\n- **DAN** Danish\n- **NLD** Dutch\n- **ENG** English\n- **EST** Estonian\n- **FIL** Filipino\n- **FIN** Finnish\n- **FRA** French\n- **GLG** Galician\n- **KAT** Georgian\n- **DEU** German\n- **ELL** Greek\n- **GUJ** Gujarati\n- **HAU** Hausa\n- **HEB** Hebrew\n- **HIN** Hindi\n- **HUN** Hungarian\n- **ISL** Icelandic\n- **IND** Indonesian\n- **GLE** Irish\n- **ITA** Italian\n- **JPN** Japanese\n- **JAV** Javanese\n- **KAN** Kannada\n- **KAZ** Kazakh\n- **KIR** Kirghiz\n- **KOR** Korean\n- **LAV** Latvian\n- **LIN** Lingala\n- **LIT** Lithuanian\n- **LTZ** Luxembourgish\n- **MKD** Macedonian\n- **MSA** Malay\n- **MAL** Malayalam\n- **CMN** Mandarin Chinese\n- **MAR** Marathi\n- **NEP** Nepali\n- **NOR** Norwegian\n- **PUS** Pashto\n- **FAS** Persian\n- **POL** Polish\n- **POR** Portuguese\n- **PAN** Punjabi\n- **RON** Romanian\n- **RUS** Russian\n- **SR",
  "created_at": "2023-02-27T09:34:46Z",
  "edited_at": "2026-05-29T16:02:38Z",
  "id": 13313366263441,
  "labels": [
    "languages",
    "language",
    "Chinese",
    "dutch",
    "Japanese",
    "عربي",
    "arabic",
    "korean"
  ],
  "locale": "en-us",
  "observed_at_ms": 1792693979067,
  "section": {
    "id": 13167144801169,
    "name": "Other",
    "url": "https://help.elevenlabs.io/hc/en-us/sections/13167144801169-Other"
  },
  "title": "What languages do you support?",
  "truncated": true,
  "updated_at": "2026-05-29T16:02:38Z",
  "url": "https://help.elevenlabs.io/hc/en-us/articles/13313366263441-What-languages-do-you-support",
  "vote_count": 6,
  "vote_sum": 2
}
```

### Get model

- Capability: `developer-docs/get_model`
- Description: One ElevenLabs model by id from the official models page: the same fields as list_models plus the Markdown of the page section that describes the model (use cases, supported languages, considerations), `max_chars› truncates. `content› is null when the page has no section for that model. Unknown ids are `not_found›.
- Instructions: To read what a specific model is for and which languages it supports, e.g. eleven_v3 or scribe_v2_realtime.
- Cost: 5 credits per call
- Capability file: [Get model](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/get_model)

Accepted options:
- `max_chars` (number): Truncate `content›; whole section when omitted. Example: `200`
- `model_id` (string, required): Model id, e.g. `eleven_multilingual_v2›. Example: `<model_id>`

Response schema example:
```json
{
  "approx_audio_duration": "~10 minutes",
  "character_limit": 10000,
  "chars": 1366,
  "content": "## Multilingual v2\n\nEleven Multilingual v2 is a previous generation emotionally-aware speech synthesis model. It produces natural, lifelike speech with high emotional range and contextual understanding across multiple languages.\n\nThe model delivers consistent voice quality and personality across all supported languages while maintaining the speaker's unique characteristics and accent.\n\nThis model excels in scenarios requiring high-quality, emotionally nuanced speech:\n\n* **Character Voiceovers**: Ideal for gaming and animation due to its emotional range.\n* **Professional Content**: Well-suited for corporate videos and e-learning materials.\n* **Multilingual Projects**: Maintains consistent voice quality across language switches.\n* **Stable Quality**: Produces consistent, high-quality audio output.\n\nWhile it has a higher latency & cost per character than Flash models, it delivers superior quality for projects where lifelike speech is important.\n\nOur multilingual v2 models support 29 languages:\n\n*English (USA, UK, Australia, Canada), Japanese, Chinese, German, Hindi, French (France, Canada), Korean, Portuguese (Brazil, Portugal), Italian, Spanish (Spain, Mexico), Indonesian, Dutch, Turkish, Filipino, Polish, Swedish, Bulgarian, Romanian, Arabic (Saudi Arabia, UAE), Czech, Greek, Finnish, Croatian, Malay, Slovak, Danish, Tamil, Ukrainian & Russian.*",
  "description": "Our lifelike model with rich emotional expression",
  "language_codes": [
    "en",
    "ja",
    "zh",
    "de",
    "hi",
    "fr",
    "ko",
    "pt",
    "it",
    "es",
    "id",
    "nl",
    "tr",
    "fil",
    "pl",
    "sv",
    "bg",
    "ro",
    "ar",
    "cs",
    "el",
    "fi",
    "hr",
    "ms",
    "sk",
    "da",
    "ta",
    "uk",
    "ru"
  ],
  "languages": "en, ja, zh, de, hi, fr, ko, pt, it, es, id, nl, tr, fil, pl, sv, bg, ro, ar, cs, el, fi, hr, ms, sk, da, ta, uk, ru",
  "latency_ms": null,
  "model_id": "eleven_multilingual_v2",
  "observed_at_ms": 1792695902017,
  "replacement": null,
  "section": {
    "anchor": "multilingual-v2",
    "text": "Multilingual v2",
    "url": "https://elevenlabs.io/docs/overview/models#multilingual-v2"
  },
  "source_url": "https://elevenlabs.io/docs/overview/models",
  "status": "current",
  "truncated": false
}
```

### Get page

- Capability: `developer-docs/get_page`
- Description: One ElevenLabs developer docs page as clean Markdown from its official `.md` twin (elevenlabs.io/docs/{path}.md): title, description, URL, an outline of every heading (level, text, anchor) and the content. Pass `section` (heading text or anchor) for only that heading's subtree; `max_chars` truncates. Accepts a docs path or an elevenlabs.io/docs URL (an anchor selects that section). Unknown pages and sections are `not_found`.
- Instructions: To read official guidance such as the models overview, latency tips, streaming or agent setup, ideally one section at a time.
- Cost: 5 credits per call
- Capability file: [Get page](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/get_page)

Accepted options:
- `max_chars` (number): Truncate `content`; whole text when omitted. Example: `200`
- `path` (string): Docs path such as `overview/models` (a `/docs/` prefix, `.md` suffix or `#anchor` is accepted). Example: `overview/models`
- `section` (string): Heading text or anchor, e.g. `Models overview`. Example: `Models overview`
- `url` (string): Alternatively a docs URL, e.g. https://elevenlabs.io/docs/overview/models#eleven-v3. Pattern: ^https?://. Example: `<url>`

Response schema example:
```json
{
  "chars": 10834,
  "content": "## Models overview\n\nThe ElevenLabs API offers a range of audio models optimized for different use cases, quality levels, and performance requirements.\n\n| Model ID                     | Description                                                                                                                                                                            | Languages                                                                                                                                                                     |\n| ---------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `eleven_v4`                  | Our most emotionally rich, expressive speech synthesis model                                                                                                                           | [90+ languages](/docs/overview/models#supported-languages)                                                                                                                    |\n| `eleven_v4_turbo`            | Our most expressive, real-time speech synthesis model (\\~100ms†)                                                                     ",
  "description": "Learn about the models that power the ElevenLabs API.",
  "markdown_url": "https://elevenlabs.io/docs/overview/models.md",
  "observed_at_ms": 1792693978959,
  "outline": [
    {
      "anchor": "models-overview",
      "level": 2,
      "text": "Models overview"
    },
    {
      "anchor": "deprecated-models",
      "level": 3,
      "text": "Deprecated models"
    }
  ],
  "path": "overview/models",
  "section": {
    "anchor": "models-overview",
    "level": 2,
    "text": "Models overview",
    "url": "https://elevenlabs.io/docs/overview/models#models-overview"
  },
  "title": "Models",
  "truncated": true,
  "url": "https://elevenlabs.io/docs/overview/models"
}
```

### Get pricing

- Capability: `developer-docs/get_pricing`
- Description: ElevenLabs pricing from every public pricing tab's schema.org FAQ data, no clicks needed: `plans› (elevenlabs.io/pricing) gives each plan's monthly USD price, monthly credits, seats, notes and annual-billing monthly equivalent plus the credits FAQ; `api› (elevenlabs.io/pricing/api) gives per-product API rates in USD; `agents› (elevenlabs.io/pricing/agents) gives ElevenAgents included call minutes and concurrent calls per plan plus overage, burst and telephony terms. `all› (default) returns the three tabs.
- Instructions: To answer what an ElevenLabs plan costs, how many credits or agent minutes it includes, annual pricing, or the per-character and per-minute API rates.
- Cost: 5 credits per call
- Capability file: [Get pricing](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/get_pricing)

Accepted options:
- `page` (string): `all› (default), `plans›, `api› or `agents›. Example: `all`

Response schema example:
```json
{
  "observed_at_ms": 1792695901935,
  "page": "all",
  "pages": [
    {
      "faqs": [
        {
          "answer": "Monthly price and included credits per plan: Free $0 (10,000 credits); Starter $6 (30,000 credits); Creator $22 (121,000 credits, $11 for the first month); Pro $99 (600,000 credits); Scale $299 (1,800,000 credits, 3 seats); Business $990 (6,000,000 credits, 10 seats); Enterprise is custom. Credits are shared across every product — see the per-product credit costs below.",
          "question": "How much does each plan cost and what is included?"
        },
        {
          "answer": "Each text character you generate consumes credits, with the exact cost depending on the model used. For V2 Multilingual models, 1 text character equals 1 credit. For V2 Flash/Turbo English and V2.5 Flash/Turbo Multilingual models, discounted pricing applies for API usage, costing between 0.5 and 1 credit per character.",
          "question": "How do text characters and credits work?"
        },
        {
          "answer": "All products draw from one shared monthly credit pool, so the same credits can be spent on any of them and using one leaves fewer for the others. Approximate credit costs are: Text to Speech 1 credit per character; Speech to Text 330 credits per minute; Eleven Music 900 credits per minute; Sound Effects 200 credits per generation; Voice Changer and Voice Isolator 1,000 credits per minute; and Dubbing 2,000 credits per minute (automatic with watermark), 3,000 (automatic without watermark), 5,000 (Dubbing Studio with watermark) or 10,000 (Dubbing Studio without watermark).",
          "question": "How many credits does each product use?"
        },
        {
          "answer": "Your credit allowance resets at the start of each billing cycle, which begins on the day you subscribed. Unused credits roll over for up to two months — up to 2× your monthly quota — so your balance can reach at most 3× your monthly quota (this month's allotment plus up to two months of rollover), as long as you maintain an active paid subscription and do not downgrade or cancel. Downgrading or cancelling forfeits unused credits at the end of the cycle. Rollover does not apply to the Free plan. Pay-as-you-go top-up credits are separate and are not subject to this rollover cap. When your subscription renews, you receive a new monthly allotment of credits.",
          "question": "When do my credits reset, and do unused credits roll over?"
        },
        {
          "answer": "Yes. Annual billing works out to two months free — you pay for 10 months (annual price = monthly price × 10). The equivalent monthly price on an annual plan is $5 for Starter, $18.33 for Creator, $82.50 for Pro, $249.17 for Scale, and $825 for Business.",
          "question": "Do you offer annual billing, and what does it cost?"
        },
        {
          "answer": "Yes. There is a maximum number of credits that can be used in a single generation request. The limit depends on whether you are on the Free tier or a paid subscription.",
          "question": "Is there a limit on how many credits I can use in a single request?"
        },
        {
          "answer": "Credits are charged per generation request, not per download. If you are not satisfied with the output, a limited number of free regenerations may be available as long as the content and certain settings do not change. Whether a regeneration is free is indicated before generating.",
          "question": "Am I charged for every generation?"
        },
        {
          "answer": "If you upgrade to a higher plan, any unused credits from your previous plan will roll over into the next billing cycle. If you downgrade or cancel your subscription, your subscription will remain active until the end of the current billing cycle. After that, your account will be downgraded to the Free plan and any unused paid credits will expire.",
          "question": "What happens if I upgrade, downgrade, or cancel my subscription?"
        },
        {
          "answer": "You can cancel your subscription at any time. Your subscription will remain active until the end of your current billing cycle, after which it will not renew and your account will be downgraded to the Free plan.",
          "question": "When can I cancel my subscription?"
        },
        {
          "answer": "You can view your remaining credits by logging into the platform and navigating to your subscription page from your profile menu.",
          "question": "How do I check how many credits I have remaining?"
        },
        {
          "answer": "We accept Credit Card, Apple Pay, and Google Pay. Subscriptions are billed on a monthly or yearly basis starting from the day you subscribe.",
          "question": "What kind of payment do you accept?"
        }
      ],
      "page": "plans",
      "plans": [
        {
          "annual_monthly_price_usd": null,
          "concurrent_calls": null,
          "included_minutes": null,
          "monthly_credits": 10000,
          "monthly_price_usd": 0,
          "name": "Free",
          "notes": [],
          "raw": "Free $0 (10,000 credits)",
          "seats": null
        },
        {
          "annual_monthly_price_usd": 5,
          "concurrent_calls": null,
          "included_minutes": null,
          "monthly_credits": 30000,
          "monthly_price_usd": 6,
          "name": "Starter",
          "notes": [],
          "raw": "Starter $6 (30,000 credits)",
          "seats": null
        },
        {
          "annual_monthly_price_usd": 18.33,
          "concurrent_calls": null,
          "included_minutes": null,
          "monthly_credits": 121000,
          "monthly_price_usd": 22,
          "name": "Creator",
          "notes": [
            "$11 for the first month"
          ],
          "raw": "Creator $22 (121,000 credits, $11 for the first month)",
          "seats": null
        },
        {
          "annual_monthly_price_usd": 82.5,
          "concurrent_calls": null,
          "included_minutes": null,
          "monthly_credits": 600000,
          "monthly_price_usd": 99,
          "name": "Pro",
          "notes": [],
          "raw": "Pro $99 (600,000 credits)",
          "seats": null
        },
        {
          "annual_monthly_price_usd": 249.17,
          "concurrent_calls": null,
          "included_minutes": null,
          "monthly_credits": 1800000,
          "monthly_price_usd": 299,
          "name": "Scale",
          "notes": [],
          "raw": "Scale $299 (1,800,000 credits, 3 seats)",
          "seats": 3
        },
        {
          "annual_monthly_price_usd": 825,
          "concurrent_calls": null,
          "included_minutes": null,
          "monthly_credits": 6000000,
          "monthly_price_usd": 990,
          "name": "Business",
          "notes": [],
          "raw": "Business $990 (6,000,000 credits, 10 seats)",
          "seats": 10
        },
        {
          "annual_monthly_price_usd": null,
          "concurrent_calls": null,
          "included_minutes": null,
          "monthly_credits": null,
          "monthly_price_usd": null,
          "name": "Enterprise",
          "notes": [
            "custom pricing"
          ],
          "raw": "Enterprise is custom",
          "seats": null
        }
      ],
      "title": "Pricing",
      "url": "https://elevenlabs.io/pricing"
    },
    {
      "faqs": [
        {
          "answer": "API usage is billed in US dollars, not credits. Text to Speech $0.08 per 1,000 characters (multilingual models) or $0.04 (Flash/Turbo). Speech to Text $0.22 per hour (Scribe) or $0.39 per hour (Scribe realtime), with keyterm prompting $0.05 per hour and transcript editing $0.07 per hour. Eleven Music $0.15 per minute. Voice Changer and Voice Isolator $0.12 per minute. Sound Effects $0.12 per minute. Dubbing $0.33 per minute (automatic with watermark), $0.50 (automatic without watermark) or $0.50 (Dubbing Studio). Prices exclude taxes.",
          "question": "What are the per-product API rates?"
        },
        {
          "answer": "Text to Speech is billed per character. Speech to Text is billed per audio minute. Music and Sound Effects are billed per generation. Dubbing is billed per source audio minute.",
          "question": "How is usage metered?"
        },
        {
          "answer": "You can view how many characters/minutes you've used by logging into the ElevenLabs platform and navigating to the analytics tab within the Developers dashboard.",
          "question": "How will I know how many characters/minutes I've used each month?"
        },
        {
          "answer": "Yes. You can reference any voice in your library by ID, including professional voices, cloned voices, and voices you've designed.",
          "question": "Can I use custom voices via API?"
        },
        {
          "answer": "Yes. Enterprise plans include dedicated support, SLAs, custom rate limits, SSO, SOC 2 compliance, and MSAs.",
          "question": "Do you offer an Enterprise plan and support?"
        },
        {
          "answer": "If you upgrade to a higher plan, any unused credits from your previous plan will roll over into the next billing cycle. If you downgrade or cancel your subscription, your subscription will remain active until the end of the current billing cycle. After that, your account will be downgraded to the Free plan and any unused paid credits will expire.",
          "question": "What happens if I upgrade, downgrade, or cancel my subscription?"
        },
        {
          "answer": "You can cancel your subscription at any time. Your subscription will remain active until the end of your current billing cycle, after which it will not renew and your account will be downgraded to the Free plan.",
          "question": "When can I cancel my subscription?"
        },
        {
          "answer": "We accept Credit Card, Apple Pay, and Google Pay. Subscriptions are billed on a monthly or yearly basis starting from the day you subscribe.",
          "question": "What kind of payment do you accept?"
        }
      ],
      "page": "api",
      "plans": [],
      "title": "ElevenAPI Pricing",
      "url": "https://elevenlabs.io/pricing/api"
    },
    {
      "faqs": [
        {
          "answer": "ElevenAgents plans are billed by call minutes, not by the shared credit pool. Included call minutes and concurrent calls per plan: Free 15 minutes / 4 concurrent calls; Starter 75 minutes / 6; Creator 275 minutes / 10; Pro 1,238 minutes / 20; Scale 3,738 minutes / 30; Business 12,375 minutes / 40. Additional call minutes cost $0.08 per minute (burst pricing $0.16 per minute, double the standard rate, when you exceed your concurrency limit), and text messages cost $0.003 each. LLM usage is billed separately on top, based on the model you choose. ElevenLabs does not charge extra for telephony, but if you connect an external provider such as Twilio or a SIP trunk, that provider bills you directly for its own charges.",
          "question": "How much do ElevenAgents plans cost per minute, and what is included?"
        },
        {
          "answer": "There is no limit to the number of agents you can create on any plan. You are only limited by the number of concurrent calls available on your plan along with your monthly credit limit.",
          "question": "How many agents can I create?"
        },
        {
          "answer": "With ElevenLabs agents, you may select from supported third-party models or you may connect a custom model with a server integration. You may also select optional LLM-enabled features to use with agents. Applicable fees for model usage are shown in the platform's user interface and will be deducted from your ElevenLabs credits.",
          "question": "What is the cost of using an LLM with my voice agent?"
        },
        {
          "answer": "No. Telephony is included on every plan, and phone calls are billed at the same call-minute rate as any other channel, so ElevenLabs adds no telephony fee. You connect your own provider, such as Twilio or a SIP trunk, and that provider bills you directly for the carrier side of the call at whatever rate you have with them.",
          "question": "Do you charge extra for telephony?"
        },
        {
          "answer": "Burst pricing allows your ElevenLabs agents to temporarily exceed your workspace's subscription concurrency limit during high-demand periods. When enabled, your agents can handle up to 3 times your normal concurrency limit, with excess calls charged at double the standard rate.",
          "question": "What is burst pricing?"
        },
        {
          "answer": "If you upgrade to a higher plan, any unused credits from your previous plan will roll over into the next billing cycle. If you downgrade or cancel your subscription, your subscription will remain active until the end of the current billing cycle. After that, your account will be downgraded to the Free plan and any unused paid credits will expire.",
          "question": "What happens if I upgrade, downgrade, or cancel my subscription?"
        },
        {
          "answer": "You can cancel your subscription at any time. Your subscription will remain active until the end of your current billing cycle, after which it will not renew and your account will be downgraded to the Free plan.",
          "question": "When can I cancel my subscription?"
        },
        {
          "answer": "You can view your remaining credits by logging into the platform and navigating to your subscription page from your profile menu.",
          "question": "How do I check how many credits I have remaining?"
        },
        {
          "answer": "We accept Credit Card, Apple Pay, and Google Pay. Subscriptions are billed on a monthly or yearly basis starting from the day you subscribe.",
          "question": "What kind of payment do you accept?"
        }
      ],
      "page": "agents",
      "plans": [
        {
          "annual_monthly_price_usd": null,
          "concurrent_calls": 4,
          "included_minutes": 15,
          "monthly_credits": null,
          "monthly_price_usd": null,
          "name": "Free",
          "notes": [],
          "raw": "Free 15 minutes / 4 concurrent calls",
          "seats": null
        },
        {
          "annual_monthly_price_usd": null,
          "concurrent_calls": 6,
          "included_minutes": 75,
          "monthly_credits": null,
          "monthly_price_usd": null,
          "name": "Starter",
          "notes": [],
          "raw": "Starter 75 minutes / 6",
          "seats": null
        },
        {
          "annual_monthly_price_usd": null,
          "concurrent_calls": 10,
          "included_minutes": 275,
          "monthly_credits": null,
          "monthly_price_usd": null,
          "name": "Creator",
          "notes": [],
          "raw": "Creator 275 minutes / 10",
          "seats": null
        },
        {
          "annual_monthly_price_usd": null,
          "concurrent_calls": 20,
          "included_minutes": 1238,
          "monthly_credits": null,
          "monthly_price_usd": null,
          "name": "Pro",
          "notes": [],
          "raw": "Pro 1,238 minutes / 20",
          "seats": null
        },
        {
          "annual_monthly_price_usd": null,
          "concurrent_calls": 30,
          "included_minutes": 3738,
          "monthly_credits": null,
          "monthly_price_usd": null,
          "name": "Scale",
          "notes": [],
          "raw": "Scale 3,738 minutes / 30",
          "seats": null
        },
        {
          "annual_monthly_price_usd": null,
          "concurrent_calls": 40,
          "included_minutes": 12375,
          "monthly_credits": null,
          "monthly_price_usd": null,
          "name": "Business",
          "notes": [],
          "raw": "Business 12,375 minutes / 40",
          "seats": null
        }
      ],
      "title": "ElevenAgents Pricing",
      "url": "https://elevenlabs.io/pricing/agents"
    }
  ]
}
```

### List blog posts

- Capability: `developer-docs/list_blog_posts`
- Description: The latest ElevenLabs blog posts (elevenlabs.io/blog) from the official RSS feed (about 50 newest): title, URL, slug, ISO publish date, description, category (Product, Resources, Company, Customer Stories, Research) and authors. Filter by `category› and text `q›; page with `limit›/`offset›.
- Instructions: To see recent ElevenLabs announcements, launches and guides, then read one with get_blog_post.
- Cost: 5 credits per call
- Capability file: [List blog posts](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/list_blog_posts)

Accepted options:
- `category` (string): Category name, case-insensitive, e.g. `Product›. Example: `<category>`
- `limit` (number): Posts per call (default 20). Example: `10`
- `offset` (number): offset Example: `10`
- `q` (string): Text matched against title and description. Example: `<q>`

Response schema example:
```json
{
  "category": null,
  "count": 5,
  "limit": 5,
  "next_offset": 5,
  "observed_at_ms": 1792695902027,
  "offset": 0,
  "posts": [
    {
      "authors": [
        "John Durovsik"
      ],
      "category": "Product",
      "description": "Learn how Cadence uses ElevenAgents to reach patients within minutes of a vital sign reading outside the expected range.",
      "published": "2026-10-21",
      "slug": "webinar-recap-reaching-at-risk-patients-when-minutes-matter",
      "title": "Webinar Recap: Reaching At-Risk Patients When Minutes Matter",
      "url": "https://elevenlabs.io/blog/webinar-recap-reaching-at-risk-patients-when-minutes-matter"
    },
    {
      "authors": [
        "Jack Limebear"
      ],
      "category": "Resources",
      "description": "Learn how to integrate Text to Speech into your application in four steps: create an API key, install the SDK, send your first request, and play the audio.",
      "published": "2026-10-21",
      "slug": "how-to-integrate-text-to-speech",
      "title": "How to integrate Text to Speech into your applications",
      "url": "https://elevenlabs.io/blog/how-to-integrate-text-to-speech"
    },
    {
      "authors": [
        "Eric Michaelis"
      ],
      "category": "Product",
      "description": "Deliver live, expressive voice translation in more than 90 languages. Available for enterprises via ElevenAPI",
      "published": "2026-10-21",
      "slug": "realtime-translation",
      "title": "Talk to anyone, in any language, in realtime",
      "url": "https://elevenlabs.io/blog/realtime-translation"
    },
    {
      "authors": [
        "Jack Limebear"
      ],
      "category": "Resources",
      "description": "Learn how to transcribe a podcast with AI in five steps, format the transcript as SRT or VTT, and publish it on podcast platforms and your website.",
      "published": "2026-10-20",
      "slug": "how-to-transcribe-a-podcast",
      "title": "How to transcribe a podcast: A step-by-step guide",
      "url": "https://elevenlabs.io/blog/how-to-transcribe-a-podcast"
    },
    {
      "authors": [
        "Min Kim"
      ],
      "category": "Product",
      "description": "Eleven Realtime is a new class of Speech to Speech models for voice agents that sound natural. Available in ElevenAgents and the Realtime API.",
      "published": "2026-10-20",
      "slug": "realtime",
      "title": "Introducing Eleven Realtime: a simpler way to build natural voice agents",
      "url": "https://elevenlabs.io/blog/realtime"
    }
  ],
  "q": null,
  "source_url": "https://elevenlabs.io/blog/rss.xml",
  "total": 50
}
```

### List changelog

- Capability: `developer-docs/list_changelog`
- Description: The ElevenLabs product and API changelog (elevenlabs.io/docs/changelog) as dated entries newest first: ISO date, heading anchor and URL, topics (the entry's subheadings, e.g. Eleven Realtime, SDK releases), and the entry's Markdown including new and updated endpoints, cut at `max_chars_per_entry›. Filter with `since› (YYYY-MM-DD) and a text `q›; page with `limit›/`offset›.
- Instructions: To see what ElevenLabs shipped recently or since a date, e.g. new models, endpoints or SDK releases.
- Cost: 5 credits per call
- Capability file: [List changelog](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/list_changelog)

Accepted options:
- `limit` (number): Entries per call (default 5). Example: `10`
- `max_chars_per_entry` (number): Cut each entry's content (default 4000). Example: `200`
- `offset` (number): offset Example: `10`
- `q` (string): Case-insensitive text the entry must contain. Example: `<q>`
- `since` (string): Only entries on or after this date. Pattern: ^\d{4}-\d{2}-\d{2}$. Example: `<since>`

Response schema example:
```json
{
  "count": 2,
  "entries": [
    {
      "anchor": "october-19-2026",
      "chars": 22701,
      "content": "### Eleven Realtime\n\nEleven Realtime is a new family of models for ElevenAgents voice agents, rolling out gradually across workspaces. Each one is a complete voice agent configuration. You pick one model, and ElevenLabs handles the LLM, Speech to Text and Text to Speech settings behind it. Your agent's system prompt, voice, tools and knowledge base work the same as before.\n\nThere are two to choose from. Eleven Realtime v1 Mini (`eleven_realtime_v1_mini`) is the default, and it's the fastest and cheapest. Eleven Realtime v1 Max (`eleven_realtime_v1_max`) reasons before it answers, so use it when your agent has complex instructions or multi-step tool calls.\n\nIf you've already built on OpenAI's Realtime API, you don't need to rewrite your client. The events and the WebSocket transport are the same, so you change the endpoint and the session configuration. Your backend calls [Create realtime client secret](/docs/api-reference/conversations/create-client-secret) to get a short-lived secret,",
      "date": "2026-10-19",
      "date_raw": "October 19, 2026",
      "topics": [
        "Eleven Realtime",
        "Realtime Translation",
        "Video to Music",
        "ElevenAgents",
        "Music and Sound Effects",
        "Speech Engine",
        "Dubbing",
        "Voices",
        "Workspaces",
        "SDK releases",
        "API",
        "ElevenAgents",
        "Workspaces",
        "ElevenAgents",
        "Text to Speech and Text to Dialogue",
        "Music",
        "Sound Effects",
        "Speech Engine",
        "Speech to Text",
        "Dubbing",
        "Voices",
        "Workspaces"
      ],
      "truncated": true,
      "url": "https://elevenlabs.io/docs/changelog#october-19-2026"
    },
    {
      "anchor": "october-12-2026",
      "chars": 13040,
      "content": "### ElevenAgents\n\n- **Merge and search triage tickets**: [Merge tickets](/docs/api-reference/triage-tickets/merge) folds up to 50 open tickets from the same agent into one target ticket. Merged tickets keep the status `merged` and reference the target through `merged_into_ticket_id`. [List tickets](/docs/api-reference/triage-tickets/list) and [List workspace tickets](/docs/api-reference/triage-tickets/list-for-workspace) add a case-insensitive `search` parameter that matches ticket titles, descriptions, comments and turn comments, and each result includes a `search_match` excerpt showing where the query matched.\n- **Workflow End node outcomes**: Workflow End nodes accept an `outcome` of `success` (default) or `failure`, so a workflow can record whether a conversation ended successfully. The conversation error type adds `workflow_end_failure`.\n- **Call queueing enabled for new agents**: New agents are created with [call queueing](/docs/eleven-agents/guides/call-queueing) enabled unless ",
      "date": "2026-10-12",
      "date_raw": "October 12, 2026",
      "topics": [
        "ElevenAgents",
        "Text to Speech",
        "Speech to Text",
        "Voices",
        "Workspaces",
        "SDK releases",
        "API",
        "ElevenAgents",
        "Voices",
        "Audio effects",
        "ElevenAgents",
        "Text to Speech",
        "Text to Dialogue",
        "Speech to Text",
        "Music",
        "History",
        "Workspace and user"
      ],
      "truncated": true,
      "url": "https://elevenlabs.io/docs/changelog#october-12-2026"
    }
  ],
  "latest_date": "2026-10-19",
  "limit": 2,
  "next_offset": 2,
  "observed_at_ms": 1792695902022,
  "offset": 0,
  "q": null,
  "since": null,
  "source_url": "https://elevenlabs.io/docs/changelog",
  "total": 20
}
```

### List models

- Capability: `developer-docs/list_models`
- Description: Every ElevenLabs API model from the official models page (elevenlabs.io/docs/overview/models): model id, description, languages (text plus language codes when listed), latency in ms when stated, character limit and approximate audio duration from the character limits table, status (current or deprecated), replacement for deprecated models and the docs section that describes it. Filter with `q›; `include_deprecated› defaults to true.
- Instructions: To pick a model id (e.g. eleven_v3, eleven_flash_v2_5, scribe_v2), check languages, character limits or latency, or see which models are deprecated.
- Cost: 5 credits per call
- Capability file: [List models](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/list_models)

Accepted options:
- `include_deprecated` (boolean): Include deprecated models (default true). Example: `false`
- `q` (string): Substring of the model id or description, e.g. `flash› or `speech recognition›. Example: `flash› or `

Response schema example:
```json
{
  "count": 23,
  "include_deprecated": true,
  "models": [
    {
      "approx_audio_duration": "~10 minutes",
      "character_limit": 10000,
      "description": "Our most emotionally rich, expressive speech synthesis model",
      "language_codes": [],
      "languages": "90+ languages",
      "latency_ms": null,
      "model_id": "eleven_v4",
      "replacement": null,
      "section": {
        "anchor": "eleven-v4",
        "text": "Eleven v4",
        "url": "https://elevenlabs.io/docs/overview/models#eleven-v4"
      },
      "status": "current"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "Our most expressive, real-time speech synthesis model (~100ms)",
      "language_codes": [],
      "languages": "90+ languages",
      "latency_ms": 100,
      "model_id": "eleven_v4_turbo",
      "replacement": null,
      "section": {
        "anchor": "eleven-v4-turbo",
        "text": "Eleven v4 Turbo",
        "url": "https://elevenlabs.io/docs/overview/models#eleven-v4-turbo"
      },
      "status": "current"
    },
    {
      "approx_audio_duration": "~5 minutes",
      "character_limit": 5000,
      "description": "Human-like and expressive speech generation",
      "language_codes": [],
      "languages": "70+ languages",
      "latency_ms": null,
      "model_id": "eleven_v3",
      "replacement": null,
      "section": {
        "anchor": "eleven-v3",
        "text": "Eleven v3",
        "url": "https://elevenlabs.io/docs/overview/models#eleven-v3"
      },
      "status": "current"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "Our most expressive, realtime speech synthesis model (~280ms)",
      "language_codes": [],
      "languages": "70+ languages",
      "latency_ms": 280,
      "model_id": "eleven_v3_conversational",
      "replacement": null,
      "section": {
        "anchor": "eleven-v3-conversational",
        "text": "Eleven v3 Conversational",
        "url": "https://elevenlabs.io/docs/overview/models#eleven-v3-conversational"
      },
      "status": "current"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "Human-like and expressive voice design model (Text to Voice)",
      "language_codes": [],
      "languages": "70+ languages",
      "latency_ms": null,
      "model_id": "eleven_ttv_v3",
      "replacement": null,
      "section": null,
      "status": "current"
    },
    {
      "approx_audio_duration": "~10 minutes",
      "character_limit": 10000,
      "description": "Our lifelike model with rich emotional expression",
      "language_codes": [
        "en",
        "ja",
        "zh",
        "de",
        "hi",
        "fr",
        "ko",
        "pt",
        "it",
        "es",
        "id",
        "nl",
        "tr",
        "fil",
        "pl",
        "sv",
        "bg",
        "ro",
        "ar",
        "cs",
        "el",
        "fi",
        "hr",
        "ms",
        "sk",
        "da",
        "ta",
        "uk",
        "ru"
      ],
      "languages": "en, ja, zh, de, hi, fr, ko, pt, it, es, id, nl, tr, fil, pl, sv, bg, ro, ar, cs, el, fi, hr, ms, sk, da, ta, uk, ru",
      "latency_ms": null,
      "model_id": "eleven_multilingual_v2",
      "replacement": null,
      "section": {
        "anchor": "multilingual-v2",
        "text": "Multilingual v2",
        "url": "https://elevenlabs.io/docs/overview/models#multilingual-v2"
      },
      "status": "current"
    },
    {
      "approx_audio_duration": "~40 minutes",
      "character_limit": 40000,
      "description": "Ultra-fast model optimized for real-time use (~75ms)",
      "language_codes": [
        "hu",
        "no",
        "vi"
      ],
      "languages": "All eleven_multilingual_v2 languages plus: hu, no, vi",
      "latency_ms": 75,
      "model_id": "eleven_flash_v2_5",
      "replacement": null,
      "section": {
        "anchor": "flash-v25",
        "text": "Flash v2.5",
        "url": "https://elevenlabs.io/docs/overview/models#flash-v25"
      },
      "status": "current"
    },
    {
      "approx_audio_duration": "~30 minutes",
      "character_limit": 30000,
      "description": "Ultra-fast model optimized for real-time use (~75ms)",
      "language_codes": [
        "en"
      ],
      "languages": "en",
      "latency_ms": 75,
      "model_id": "eleven_flash_v2",
      "replacement": null,
      "section": null,
      "status": "current"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "State-of-the-art multilingual voice changer model (Speech to Speech)",
      "language_codes": [
        "en",
        "ja",
        "zh",
        "de",
        "hi",
        "fr",
        "ko",
        "pt",
        "it",
        "es",
        "id",
        "nl",
        "tr",
        "fil",
        "pl",
        "sv",
        "bg",
        "ro",
        "ar",
        "cs",
        "el",
        "fi",
        "hr",
        "ms",
        "sk",
        "da",
        "ta",
        "uk",
        "ru"
      ],
      "languages": "en, ja, zh, de, hi, fr, ko, pt, it, es, id, nl, tr, fil, pl, sv, bg, ro, ar, cs, el, fi, hr, ms, sk, da, ta, uk, ru",
      "latency_ms": null,
      "model_id": "eleven_multilingual_sts_v2",
      "replacement": null,
      "section": null,
      "status": "current"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "State-of-the-art multilingual voice designer model (Text to Voice)",
      "language_codes": [
        "en",
        "ja",
        "zh",
        "de",
        "hi",
        "fr",
        "ko",
        "pt",
        "it",
        "es",
        "id",
        "nl",
        "tr",
        "fil",
        "pl",
        "sv",
        "bg",
        "ro",
        "ar",
        "cs",
        "el",
        "fi",
        "hr",
        "ms",
        "sk",
        "da",
        "ta",
        "uk",
        "ru"
      ],
      "languages": "en, ja, zh, de, hi, fr, ko, pt, it, es, id, nl, tr, fil, pl, sv, bg, ro, ar, cs, el, fi, hr, ms, sk, da, ta, uk, ru",
      "latency_ms": null,
      "model_id": "eleven_multilingual_ttv_v2",
      "replacement": null,
      "section": null,
      "status": "current"
    },
    {
      "approx_audio_duration": "~10 minutes",
      "character_limit": 10000,
      "description": "English-only voice changer model (Speech to Speech)",
      "language_codes": [
        "en"
      ],
      "languages": "en",
      "latency_ms": null,
      "model_id": "eleven_english_sts_v2",
      "replacement": null,
      "section": null,
      "status": "current"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "Real-time speech recognition model",
      "language_codes": [],
      "languages": "90+ languages",
      "latency_ms": null,
      "model_id": "scribe_v2_realtime",
      "replacement": null,
      "section": {
        "anchor": "scribe-v2-realtime",
        "text": "Scribe v2 Realtime",
        "url": "https://elevenlabs.io/docs/overview/models#scribe-v2-realtime"
      },
      "status": "current"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "State-of-the-art speech recognition model",
      "language_codes": [],
      "languages": "90+ languages",
      "latency_ms": null,
      "model_id": "scribe_v2",
      "replacement": null,
      "section": {
        "anchor": "scribe-v2",
        "text": "Scribe v2",
        "url": "https://elevenlabs.io/docs/overview/models#scribe-v2"
      },
      "status": "current"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "Speech recognition model specialized for medical and clinical audio",
      "language_codes": [],
      "languages": "90+ languages",
      "latency_ms": null,
      "model_id": "scribe_v2_medical",
      "replacement": null,
      "section": {
        "anchor": "scribe-v2-medical",
        "text": "Scribe v2 Medical",
        "url": "https://elevenlabs.io/docs/overview/models#scribe-v2-medical"
      },
      "status": "current"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "Complete voice agent model configuration, optimized for fast, natural conversation",
      "language_codes": [],
      "languages": "90+ languages",
      "latency_ms": null,
      "model_id": "eleven_realtime_v1_mini",
      "replacement": null,
      "section": {
        "anchor": "eleven-realtime",
        "text": "Eleven Realtime",
        "url": "https://elevenlabs.io/docs/overview/models#eleven-realtime"
      },
      "status": "current"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "Complete voice agent model configuration, optimized for complex, multi-step tasks",
      "language_codes": [],
      "languages": "90+ languages",
      "latency_ms": null,
      "model_id": "eleven_realtime_v1_max",
      "replacement": null,
      "section": {
        "anchor": "eleven-realtime",
        "text": "Eleven Realtime",
        "url": "https://elevenlabs.io/docs/overview/models#eleven-realtime"
      },
      "status": "current"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "Sound effects generation from text prompts",
      "language_codes": [],
      "languages": "N/A",
      "latency_ms": null,
      "model_id": "eleven_text_to_sound_v2",
      "replacement": null,
      "section": null,
      "status": "current"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "Our most advanced music model. Studio-grade generation from text prompts, composition plans and previously generated songs, with improved quality and prompt adherence over music_v2",
      "language_codes": [
        "en",
        "es",
        "de",
        "ja"
      ],
      "languages": "en, es, de, ja, and more",
      "latency_ms": null,
      "model_id": "music_v2_5",
      "replacement": null,
      "section": {
        "anchor": "eleven-music",
        "text": "Eleven Music",
        "url": "https://elevenlabs.io/docs/overview/models#eleven-music"
      },
      "status": "current"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "Studio-grade music generation from text prompts, composition plans and previously generated songs",
      "language_codes": [
        "en",
        "es",
        "de",
        "ja"
      ],
      "languages": "en, es, de, ja, and more",
      "latency_ms": null,
      "model_id": "music_v2",
      "replacement": null,
      "section": {
        "anchor": "eleven-music",
        "text": "Eleven Music",
        "url": "https://elevenlabs.io/docs/overview/models#eleven-music"
      },
      "status": "current"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "Studio-grade music generation from text prompts. Outclassed by music_v2 and music_v2_5",
      "language_codes": [
        "en",
        "es",
        "de",
        "ja"
      ],
      "languages": "en, es, de, ja, and more",
      "latency_ms": null,
      "model_id": "music_v1",
      "replacement": null,
      "section": {
        "anchor": "eleven-music",
        "text": "Eleven Music",
        "url": "https://elevenlabs.io/docs/overview/models#eleven-music"
      },
      "status": "current"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "First generation low-latency model (outclassed by Flash models)",
      "language_codes": [
        "en",
        "ja",
        "zh",
        "de",
        "hi",
        "fr",
        "ko",
        "pt",
        "it",
        "es",
        "id",
        "nl",
        "tr",
        "fil",
        "pl",
        "sv",
        "bg",
        "ro",
        "ar",
        "cs",
        "el",
        "fi",
        "hr",
        "ms",
        "sk",
        "da",
        "ta",
        "uk",
        "ru",
        "hu",
        "no",
        "vi"
      ],
      "languages": "en, ja, zh, de, hi, fr, ko, pt, it, es, id, nl, tr, fil, pl, sv, bg, ro, ar, cs, el, fi, hr, ms, sk, da, ta, uk, ru, hu, no, vi",
      "latency_ms": null,
      "model_id": "eleven_turbo_v2_5",
      "replacement": "eleven_flash_v2_5",
      "section": null,
      "status": "deprecated"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "First generation low-latency model (outclassed by Flash models)",
      "language_codes": [
        "en"
      ],
      "languages": "en",
      "latency_ms": null,
      "model_id": "eleven_turbo_v2",
      "replacement": "eleven_flash_v2",
      "section": null,
      "status": "deprecated"
    },
    {
      "approx_audio_duration": null,
      "character_limit": null,
      "description": "First generation speech recognition (outclassed by v2 models)",
      "language_codes": [],
      "languages": "90+ languages",
      "latency_ms": null,
      "model_id": "scribe_v1",
      "replacement": "scribe_v2",
      "section": null,
      "status": "deprecated"
    }
  ],
  "observed_at_ms": 1792695902012,
  "q": null,
  "source_url": "https://elevenlabs.io/docs/overview/models"
}
```

### List pages

- Capability: `developer-docs/list_pages`
- Description: List the pages of the ElevenLabs developer docs from the public llms.txt index: title, docs path, URL, Markdown URL, description and navigation breadcrumb, for guides (`docs`) and API reference endpoints (`api`). Filter by section and a case-insensitive substring `q`; page with `limit` and `offset`.
- Instructions: To enumerate docs pages or every API endpoint in a group, e.g. all Voices endpoints.
- Cost: 5 credits per call
- Capability file: [List pages](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/list_pages)

Accepted options:
- `limit` (number): Pages per call (default 100). Example: `10`
- `offset` (number): Start offset; use `next_offset` to continue. Example: `10`
- `q` (string): Substring matched against title, path, breadcrumb and description. Example: `<q>`
- `section` (string): `docs` for guides and product pages, `api` for API reference endpoints. Example: `docs`

Response schema example:
```json
{
  "count": 9,
  "limit": 20,
  "next_offset": null,
  "observed_at_ms": 1792693978954,
  "offset": 0,
  "pages": [
    {
      "breadcrumb": [
        "API reference",
        "ElevenAPI",
        "Text to Speech"
      ],
      "description": null,
      "markdown_url": "https://elevenlabs.io/docs/api-reference/text-to-speech/v-1-text-to-speech-voice-id-stream-input.md",
      "path": "api-reference/text-to-speech/v-1-text-to-speech-voice-id-stream-input",
      "section": "api",
      "title": "WebSocket",
      "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/v-1-text-to-speech-voice-id-stream-input"
    },
    {
      "breadcrumb": [
        "API reference",
        "ElevenAPI",
        "Text to Speech"
      ],
      "description": null,
      "markdown_url": "https://elevenlabs.io/docs/api-reference/text-to-speech/v-1-text-to-speech-voice-id-multi-stream-input.md",
      "path": "api-reference/text-to-speech/v-1-text-to-speech-voice-id-multi-stream-input",
      "section": "api",
      "title": "Multi-Context WebSocket",
      "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/v-1-text-to-speech-voice-id-multi-stream-input"
    },
    {
      "breadcrumb": [
        "API reference",
        "ElevenAPI",
        "Text to Speech"
      ],
      "description": null,
      "markdown_url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert.md",
      "path": "api-reference/text-to-speech/convert",
      "section": "api",
      "title": "Create speech",
      "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert"
    },
    {
      "breadcrumb": [
        "API reference",
        "ElevenAPI",
        "Text to Speech"
      ],
      "description": null,
      "markdown_url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert-with-timestamps.md",
      "path": "api-reference/text-to-speech/convert-with-timestamps",
      "section": "api",
      "title": "Create speech with timing",
      "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert-with-timestamps"
    },
    {
      "breadcrumb": [
        "API reference",
        "ElevenAPI",
        "Text to Speech"
      ],
      "description": null,
      "markdown_url": "https://elevenlabs.io/docs/api-reference/text-to-speech/stream.md",
      "path": "api-reference/text-to-speech/stream",
      "section": "api",
      "title": "Stream speech",
      "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/stream"
    },
    {
      "breadcrumb": [
        "API reference",
        "ElevenAPI",
        "Text to Speech"
      ],
      "description": null,
      "markdown_url": "https://elevenlabs.io/docs/api-reference/text-to-speech/stream-with-timestamps.md",
      "path": "api-reference/text-to-speech/stream-with-timestamps",
      "section": "api",
      "title": "Stream speech with timing",
      "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/stream-with-timestamps"
    },
    {
      "breadcrumb": [
        "API reference",
        "ElevenCreative",
        "Image & Video",
        "Flows",
        "Text to Speech"
      ],
      "description": null,
      "markdown_url": "https://elevenlabs.io/docs/api-reference/flows/text-to-speech/list.md",
      "path": "api-reference/flows/text-to-speech/list",
      "section": "api",
      "title": "List Speech Generations",
      "url": "https://elevenlabs.io/docs/api-reference/flows/text-to-speech/list"
    },
    {
      "breadcrumb": [
        "API reference",
        "ElevenCreative",
        "Image & Video",
        "Flows",
        "Text to Speech"
      ],
      "description": null,
      "markdown_url": "https://elevenlabs.io/docs/api-reference/flows/text-to-speech/create.md",
      "path": "api-reference/flows/text-to-speech/create",
      "section": "api",
      "title": "Create Speech Generation",
      "url": "https://elevenlabs.io/docs/api-reference/flows/text-to-speech/create"
    },
    {
      "breadcrumb": [
        "API reference",
        "ElevenCreative",
        "Image & Video",
        "Flows",
        "Text to Speech"
      ],
      "description": null,
      "markdown_url": "https://elevenlabs.io/docs/api-reference/flows/text-to-speech/get.md",
      "path": "api-reference/flows/text-to-speech/get",
      "section": "api",
      "title": "Get Speech Generation",
      "url": "https://elevenlabs.io/docs/api-reference/flows/text-to-speech/get"
    }
  ],
  "q": "text-to-speech",
  "section": "api",
  "source_url": "https://elevenlabs.io/docs/llms.txt",
  "total": 9
}
```

### Search docs

- Capability: `developer-docs/search_docs`
- Description: Search the official ElevenLabs developer docs (elevenlabs.io/docs) by keywords: guides, product pages and every API reference endpoint, ranked by how many query terms each page's title, path, navigation group and description contain. Returns page titles, docs paths, URLs, Markdown URLs, descriptions and navigation breadcrumbs. Built on the docs' public llms.txt index.
- Instructions: To find the docs page or API endpoint for a task (e.g. text to speech streaming, voice cloning, speech to text webhooks) before reading it with get_page or get_api_endpoint.
- Cost: 5 credits per call
- Capability file: [Search docs](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/search_docs)

Accepted options:
- `limit` (number): Results to return (default 10). Example: `10`
- `query` (string, required): Keywords, e.g. `create speech` or `voice cloning`. Example: `create speech`
- `section` (string): `docs` for guides and product pages, `api` for API reference endpoints. Example: `docs`

Response schema example:
```json
{
  "count": 5,
  "observed_at_ms": 1792693978939,
  "query": "create speech",
  "results": [
    {
      "breadcrumb": [
        "API reference",
        "ElevenAPI",
        "Text to Speech"
      ],
      "description": null,
      "markdown_url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert.md",
      "matched_terms": 2,
      "path": "api-reference/text-to-speech/convert",
      "rank": 1,
      "score": 37,
      "section": "api",
      "title": "Create speech",
      "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert"
    },
    {
      "breadcrumb": [
        "API reference",
        "ElevenAPI",
        "Speech Engine"
      ],
      "description": null,
      "markdown_url": "https://elevenlabs.io/docs/api-reference/speech-engine/create.md",
      "matched_terms": 2,
      "path": "api-reference/speech-engine/create",
      "rank": 2,
      "score": 28,
      "section": "api",
      "title": "Create Speech Engine",
      "url": "https://elevenlabs.io/docs/api-reference/speech-engine/create"
    },
    {
      "breadcrumb": [
        "API reference",
        "ElevenCreative",
        "Image & Video",
        "Flows",
        "Text to Speech"
      ],
      "description": null,
      "markdown_url": "https://elevenlabs.io/docs/api-reference/flows/text-to-speech/create.md",
      "matched_terms": 2,
      "path": "api-reference/flows/text-to-speech/create",
      "rank": 3,
      "score": 28,
      "section": "api",
      "title": "Create Speech Generation",
      "url": "https://elevenlabs.io/docs/api-reference/flows/text-to-speech/create"
    },
    {
      "breadcrumb": [
        "API reference",
        "ElevenAPI",
        "Text to Speech"
      ],
      "description": null,
      "markdown_url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert-with-timestamps.md",
      "matched_terms": 2,
      "path": "api-reference/text-to-speech/convert-with-timestamps",
      "rank": 4,
      "score": 25,
      "section": "api",
      "title": "Create speech with timing",
      "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert-with-timestamps"
    },
    {
      "breadcrumb": [
        "API reference",
        "ElevenAPI",
        "Speech to Text"
      ],
      "description": null,
      "markdown_url": "https://elevenlabs.io/docs/api-reference/speech-to-text/convert.md",
      "matched_terms": 2,
      "path": "api-reference/speech-to-text/convert",
      "rank": 5,
      "score": 11,
      "section": "api",
      "title": "Create transcript",
      "url": "https://elevenlabs.io/docs/api-reference/speech-to-text/convert"
    }
  ],
  "section": "api",
  "source_url": "https://elevenlabs.io/docs/llms.txt"
}
```

### Search help articles

- Capability: `developer-docs/search_help_articles`
- Description: Search the ElevenLabs help center (help.elevenlabs.io) through its public Zendesk Help Center API: article id, title, URL, section id, highlighted snippet as plain text, labels, created and updated times and vote sum, with the total match count. Page with `page`; `next_page` continues.
- Instructions: To find ElevenLabs support answers about billing, accounts, languages, voices and product behavior.
- Cost: 5 credits per call
- Capability file: [Search help articles](https://firecrawl.dev/alexandria/agents/providers/elevenlabs-io/developer-docs/search_help_articles)

Accepted options:
- `limit` (number): Results per page (default 10). Example: `10`
- `page` (number): Page number (default 1). Example: `10`
- `query` (string, required): Search words, e.g. `languages`. Example: `<query>`

Response schema example:
```json
{
  "count": 5,
  "next_page": 2,
  "observed_at_ms": 1792693979060,
  "page": 1,
  "page_count": 34,
  "per_page": 5,
  "query": "what languages do you support",
  "results": [
    {
      "created_at": "2023-02-27T09:34:46Z",
      "id": 13313366263441,
      "labels": [
        "languages",
        "language",
        "Chinese",
        "dutch",
        "Japanese",
        "عربي",
        "arabic",
        "korean"
      ],
      "section_id": 13167144801169,
      "snippet": "For details of our older models, please see What models do you offer and what is the difference between them?",
      "title": "What languages do you support?",
      "updated_at": "2026-05-29T16:02:38Z",
      "url": "https://help.elevenlabs.io/hc/en-us/articles/13313366263441-What-languages-do-you-support",
      "vote_sum": 2
    },
    {
      "created_at": "2024-10-17T16:59:54Z",
      "id": 29298127196945,
      "labels": [],
      "section_id": 29297688215825,
      "snippet": "list of supported languages, please see What languages do you support? For more information on ElevenAgents, please see our",
      "title": "Which languages can I use with ElevenAgents?",
      "updated_at": "2026-08-14T10:04:09Z",
      "url": "https://help.elevenlabs.io/hc/en-us/articles/29298127196945-Which-languages-can-I-use-with-ElevenAgents",
      "vote_sum": 0
    },
    {
      "created_at": "2023-10-05T07:45:50Z",
      "id": 19124313713041,
      "labels": [],
      "section_id": 23795023293073,
      "snippet": "speak any language currently supported by the AI; however, if you do not use a voice that is native to the language you want the",
      "title": "What languages can the AI speak?",
      "updated_at": "2024-05-08T15:54:33Z",
      "url": "https://help.elevenlabs.io/hc/en-us/articles/19124313713041-What-languages-can-the-AI-speak",
      "vote_sum": 0
    },
    {
      "created_at": "2023-10-23T12:55:50Z",
      "id": 19569659818129,
      "labels": [],
      "section_id": 23821115950481,
      "snippet": "We support Professional Voice Cloning for all languages supported by the Flash v2.5 model. Currently, these are the languages",
      "title": "What languages are supported with Professional Voice Cloning?",
      "updated_at": "2026-08-14T10:01:58Z",
      "url": "https://help.elevenlabs.io/hc/en-us/articles/19569659818129-What-languages-are-supported-with-Professional-Voice-Cloning",
      "vote_sum": 0
    },
    {
      "created_at": "2026-06-29T13:33:36Z",
      "id": 48231479965969,
      "labels": [],
      "section_id": 23795005622929,
      "snippet": "Dubbing v2 supports the following languages: English Gujarati Norwegian Slovenian Punjabi Tamil Azerbaijani Galician Icelandic",
      "title": "Which languages are supported in Dubbing v2?",
      "updated_at": "2026-06-29T13:41:04Z",
      "url": "https://help.elevenlabs.io/hc/en-us/articles/48231479965969-Which-languages-are-supported-in-Dubbing-v2",
      "vote_sum": 0
    }
  ],
  "total": 168
}
```