# ElevenLabs Speech to Text - Scribe V2

Transcribe audio and video to text with ElevenLabs Speech to Text - Scribe V2 from fal through one Spiral API key. Transcribes up to 20 minutes of MP3, WAV, M4A, OGG, FLAC or AAC audio (no video files) with word timestamps and speaker labels. It runs in the background and returns structured JSON. Pay as you go, with no subscription.

- Provider: fal
- Category: Audio
- Runs: In the background
- Returns: json
- Tool id: `fal` / `fal-ai/elevenlabs/speech-to-text/scribe-v2`
- Page: https://spiral.ai/tools/fal/fal-ai/elevenlabs/speech-to-text/scribe-v2

## Pricing

$0.0104 per minute of input audio, each started minute counted ($0.01352 with key terms).

## Limits

- Longest queue wait: 1 hour
- Run deadline: 30 minutes
- Longest run, end to end: 930 minutes
- Largest inline input: 1 MB
- Largest input file: 2 GB
- Longest input media: 20 minutes
- Largest output: 5 GB

## Input

| Field | Kind | Allowed | Default | Description |
| --- | --- | --- | --- | --- |
| `audio_url` (required) | URL or file |  | — | URL of the audio file to transcribe |
| `language_code` | text |  | — | Language code of the audio |
| `tag_audio_events` | true or false |  | true | Tag audio events like laughter, applause, etc. |
| `diarize` | true or false |  | true | Whether to annotate who is speaking |
| `keyterms` | list |  | [] | Words or sentences to bias the model towards transcribing. Up to 100 keyterms, max 50 characters each. Adds 30% premium over base transcription price. |

## Example

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/elevenlabs/speech-to-text/scribe-v2",
    "input": {
      "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/elevenlabs/scribe_v2_in.mp3"
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=fal&model=fal-ai%2Felevenlabs%2Fspeech-to-text%2Fscribe-v2

## Common questions

### ElevenLabs Speech to Text - Scribe V2

**How much does ElevenLabs Speech to Text - Scribe V2 cost?**

$0.0104 per minute of input audio, each started minute counted ($0.01352 with key terms). You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use ElevenLabs Speech to Text - Scribe V2 through an API?**

Send `POST /v1/runs` with `"provider": "fal"`, `"model": "fal-ai/elevenlabs/speech-to-text/scribe-v2"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

**Do I need an account with fal to use ElevenLabs Speech to Text - Scribe V2?**

No. Spiral runs it on its own fal account and charges your Spiral balance.

**Can my AI agent use ElevenLabs Speech to Text - Scribe V2?**

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.

