# Scribe v2

Multilingual speech-to-text with speaker diarization, word-level timestamps, and audio event tagging. Supports more than 90 languages and is billed per second of input audio.

- **Model ID:** `elevenlabs/scribe-v2`
- **Type:** transcription
- **Providers:** elevenlabs
- **Context window:** Not applicable
- **Maximum output tokens:** 0
- **Pricing:** $0.000030556/1M input tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/scribe-v2

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { experimental_transcribe as transcribe } from 'ai';
import { gateway } from '@ai-sdk/gateway';
import { readFile } from 'node:fs/promises';

const result = await transcribe({
  model: gateway.transcriptionModel('elevenlabs/scribe-v2'),
  audio: await readFile('audio.mp3'),
});
```

## Links

- [Model page](https://vercel.com/ai-gateway/models/scribe-v2)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://elevenlabs.io/docs/overview/models#scribe-v2)
- [Provider pricing](https://elevenlabs.io/pricing/api)


If you encounter incorrect information, can’t find what you need, need a capability Vercel doesn’t currently offer, or have any other feedback to report, please do it by following the instructions at https://vercel.com/feedback.md.