GET

/v1/schemas/fal/audio/fal-ai%2Fcohere-transcribe

Accept:

kind inputactivity audiohash 88a01cd0…extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

4 properties · 1 required · 0 $defs

property	type	description	constraints
audio_url*	string	URL of the audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, webm, ogg, flac.
max_new_tokens	integer	Maximum number of tokens to generate per audio chunk.	1 ≤ n ≤ 1014 · default: 256
language	enum	Language of the audio (ISO 639-1 code). Supported: en, fr, de, it, es, pt, el, nl, pl, zh, ja, ko, vi, ar.	en \| fr \| de \| it \| es \| pt · +8 more · default: "en"
punctuation	boolean	Whether to include punctuation and capitalization in the output.	default: true

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/cohere-transcribe","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}