# ElevenLabs Scribe speech to text

Needs audio url. Served by fal.ai.

ElevenLabs Scribe, speech to text, served by fal.ai. The OpenAPI schema for the fal-ai/elevenlabs/speech-to-text queue. Price: $0.03 per minute of input audio (fal meters started minutes); ElevenLabs accepts at most 10 hours per file, so $18 is reserved, metered by fal after the call (x-fal-billable-units) and billed at that reading; the reservation is the provider's documented maximum for one request and the difference is refunded. Waits up to 40 s for the result; if the generation takes longer, the run stays RUNNING and returns a request_id; poll fal/status and fetch fal/result with model "fal-ai/elevenlabs" and that request_id. Billed once, when the result is ready; a generation that fails is refunded.

- Tool ID: `fal/elevenlabs-speech-to-text`
- Name in the catalog: ElevenLabs Scribe, speech to text
- Provider: [fal.ai](/providers/fal.md)
- Capability: [Speech to text](/tools/audio-generation/speech-to-text.md)
- Price: $0.03 per unit
- Authentication: an authorised Agentik workspace is required for execution, including zero-price tools.

## Pricing contract

The provider’s price, with no markup. Billed for measured usage.


```json
{
  "model": "per_unit",
  "amountUsd": 0.03,
  "unitsHeader": "x-fal-billable-units",
  "maxUnits": 600,
  "fractional": true
}
```

Pricing source: [https://fal.ai/models/fal-ai/elevenlabs/speech-to-text](https://fal.ai/models/fal-ai/elevenlabs/speech-to-text). $0.03 per minute of input audio (fal meters started minutes); ElevenLabs accepts at most 10 hours per file, so $18 is reserved, metered by fal after the call (x-fal-billable-units) and billed at that reading; the reservation is the provider's documented maximum for one request and the difference is refunded..

Price verification date: 2026-10-08.

## Complete input schema


```json
{
  "type": "object",
  "properties": {
    "audio_url": {
      "type": "string",
      "description": "URL of the audio file to transcribe",
      "title": "Audio Url"
    },
    "language_code": {
      "type": "string",
      "title": "Language Code",
      "description": "Language code of the audio"
    },
    "tag_audio_events": {
      "type": "boolean",
      "title": "Tag Audio Events",
      "description": "Tag audio events like laughter, applause, etc.",
      "default": true
    },
    "diarize": {
      "type": "boolean",
      "title": "Diarize",
      "description": "Whether to annotate who is speaking",
      "default": true
    }
  },
  "required": [
    "audio_url"
  ],
  "additionalProperties": false
}
```

## Published example

This is the provider tool’s published example. Replace example values with the user’s requested inputs, respecting the schema; do not execute an example merely to test a connection.


```json
{
  "tool_id": "fal/elevenlabs-speech-to-text",
  "input": {
    "audio_url": "https://v3.fal.media/files/zebra/zJL_oRY8h5RWwjoK1w7tx_output.mp3"
  }
}
```

## Execute and retrieve

Inspect again before execution, explain the price and obtain the required authority. Use MCP run_tool or POST /v1/run with this tool ID, valid input and an idempotency key. Save the returned run ID and follow the actual state. If Agentik answers that the tool is temporarily unavailable, do not retry it blindly; use discovery to propose an alternative.

This tool uses deferred settlement. Follow its returned task/run instructions; preserve the existing reservation until the result is reconciled.

A partial or uncertain result can still have consumed provider resources. Consult [billing](/docs/billing.md), [idempotency](/docs/idempotency.md) and [asynchronous results](/docs/async.md).

[Provider documentation](https://fal.ai/models/fal-ai/elevenlabs/speech-to-text)

[REST inspection](https://api.agentik.cc/v1/tools/fal/elevenlabs-speech-to-text) · [OpenAPI](/openapi.json) · [Connection guide](/connect.md)

---

[HTML page](/providers/fal/elevenlabs-speech-to-text) · [Agent index](/llms.txt)