GET

/v1/schemas/fal/audio/fal-ai%2Felevenlabs%2Fspeech-to-text%2Fscribe-v2

Accept:

kind inputactivity audiohash 13eaf71f…extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

5 properties · 1 required · 0 $defs

property	type	description	constraints
audio_url*	string	URL of the audio file to transcribe
diarize	boolean	Whether to annotate who is speaking	default: true
language_code	string	Language code of the audio	nullable
keyterms	string[]	Words or sentences to bias the model towards transcribing. Up to 100 keyterms, max 50 characters each. Adds 30% premium over base transcription price.	items ≤ 100 · default: []
tag_audio_events	boolean	Tag audio events like laughter, applause, etc.	default: true

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/elevenlabs/speech-to-text/scribe-v2","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}