← All models
Cohere Transcribe turns your business audio into accurate text, ready for search, analytics, and automation
Details
- Accepts
- audio
Pricing
- Price
- 0.00868 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| language | stringenum: en, fr, de, it, es, pt… | Language of the audio (ISO 639-1 code). Supported: en, fr, de, it, es, pt, el, nl, pl, zh, ja, ko, vi, ar. |
| audio_urlrequired | string | URL of the audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, webm, ogg, flac. |
| punctuation | boolean | Whether to include punctuation and capitalization in the output. |
| max_new_tokens | integer | Maximum number of tokens to generate per audio chunk. |
Output
| Field | Type | Description |
|---|---|---|
| text | string | Transcribed text from the audio file. |
| timings | object | Performance timing breakdown in seconds. |