GET

/v1/schemas/fal/audio/kotoba-technologies/kotoba-stt/v1/speech-to-text?kind=output

Accept:

kind outputactivity audiohash 58c20928…extracted Oct 16, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `38d503d5b9daa45fa4417799564801131f8f4284a370f9d264655b83ed2172c5` { "fetchedAt": 1792126843, "extractorVersion": "1", "verifiedAt": null }

Response body

5 properties · 4 required · 1 $defs

property	type	constraints
language_code*	string
text*	string
language_probability*	number
words*	SpeechToTextWord[]
audio_duration_secs	number	nullable

Types

1 $defs

SpeechToTextWordobject

type	enum	word \| spacing \| audio_event · default: "word"
speaker_id	string	nullable
text*	string
start	number	nullable
end	number	nullable

Validate a payload

before you spend tokens

shell

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