# Scribe v1 speech to text

`elevenlabs/scribe_v1` · ElevenLabs · audio

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 page](https://sociaro.com/models/elevenlabs/scribe_v1) · [JSON](https://sociaro.com/models/elevenlabs/scribe_v1.json) · [Model pricing](https://sociaro.com/pricing?model=elevenlabs%2Fscribe_v1) · [Documentation](https://docs.sociaro.com/models/elevenlabs-scribe-v1/)

## Use cases

- Make a recorded interview searchable
- Transcribe a webinar from its video file

## Technical details

- API model ID — elevenlabs/scribe_v1
- Provider — ElevenLabs
- Modality — Audio
- Input — Audio or video file
- Output — Transcript
- Endpoint — POST /v1/audio/transcriptions

## Request parameters

- `file` (audio file (multipart), required) — The recording to transcribe, sent as a multipart form field.
  - an audio or video file
- `language` (string, optional, default `detected`) — Passed to ElevenLabs as its language_code.
  - a language code, e.g. en
- `temperature` (number, optional, default `the vendor's`) — Randomness of the transcription; lower is more literal.
  - a number, within ElevenLabs' range

## Pricing

Rates in USD. Catalogue timestamp 2026-11-21T02:23:44Z.

- USD 0.264 per hour of input audio · active · billed at $0.000073333333 a second
