GET

/v1/schemas/fal/audio/fal-ai/cohere-transcribe

kind inputactivity audiohash 88a01cd0…extracted Jul 6, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.
Source trace
2704f6865149758bf7c2257e4f7f2282e853098ba07978f1e102c0a28667cd60
{
  "fetchedAt": 1783330412,
  "extractorVersion": "1",
  "verifiedAt": null
}

Request body

4 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
audio_url*stringURL of the audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, webm, ogg, flac.
max_new_tokensintegerMaximum number of tokens to generate per audio chunk.1 ≤ n ≤ 1014 · default: 256
languageenumLanguage 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"
punctuationbooleanWhether 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", …}]}