ElevenLabs
Scribe v1 speech to text
Scribe v1 transcribes speech from an audio or video recording in over 90 languages. It can detect the language or use one you specify.
Model interface
API model ID
elevenlabs/scribe_v1- Input
- Audio or video file
- Output
- Transcript
- Endpoint
POST /v1/audio/transcriptions
Best for
- Make a recorded interview searchable
- Transcribe a webinar from its video file
Technical details
Read the model documentation- API model ID
elevenlabs/scribe_v1- Provider
- ElevenLabs
- Modality
- Audio
- Input
- Audio or video file
- Output
- Transcript
- Endpoint
POST /v1/audio/transcriptions
Request parameters
fileaudio file (multipart) · RequiredThe recording to transcribe, sent as a multipart form field.
an audio or video file
languagestring · Optional · Default: detectedPassed to ElevenLabs as its language_code.
a language code, e.g. en
temperaturenumber · Optional · Default: the vendor'sRandomness of the transcription; lower is more literal.
a number, within ElevenLabs' range
Pricing
| Billable unit and options | Rate (USD) |
|---|---|
| Per hour of input audiobilled at $0.000073333333 a second | $0.264 |
Catalogue rates on 21 Nov 2026. Prices exclude VAT.
View in pricing catalogue