← All models
Use Scribe-V2 from ElevenLabs to do blazingly fast speech to text inferences!
Details
- Accepts
- audio
Pricing
- Price
- 1 cr / minute
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| diarize | boolean | Whether to annotate who is speaking |
| keyterms | array | Words or sentences to bias the model towards transcribing. Up to 100 keyterms, max 50 characters each. Adds 30% premium over base transcription price. |
| audio_urlrequired | string | URL of the audio file to transcribe |
| language_code | — | Language code of the audio |
| tag_audio_events | boolean | Tag audio events like laughter, applause, etc. |
Output
| Field | Type | Description |
|---|---|---|
| text | string | The full transcribed text |
| words | array | Word-level transcription details |
| language_code | string | Detected or specified language code |
| language_probability | number | Confidence in language detection |