GET

/v1/schemas/fal/audio/kotoba-technologies/kotoba-stt/v1/speech-to-text

kind inputactivity audiohash 86276b9e…extracted Oct 21, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

upstream-spec

Source trace
d8337e3cde183b957e318083358bad3e3145d134f7ea00ef5bd435253f9a2818
{
  "fetchedAt": 1792558810,
  "extractorVersion": "1",
  "verifiedAt": null
}

Request body

6 properties · 2 required · 0 $defs
propertytypedescriptionconstraints
audio_url*stringSpeech to transcribe: an https:// URL on fal's CDN (Playground uploads and microphone recordings) or a base64 data: URI. Up to 2 minutes.
language*enumLanguage spoken in the audio.ja | en | ko | zh | es | zh-hk · +2 more
with_timestampsbooleanReturn `words` with start and end times for each word.default: false
kanabooleanWrite personal and place names in katakana (Japanese).default: false
keywordsstring[]Up to 1000 terms of at most 64 characters, such as names or product words, whose spelling the transcript should prefer.items ≤ 1000 · nullable
diarizationbooleanAttribute words to speakers (`speaker_id` on each word; models with speaker tokens only). Word times are null unless `with_timestamps` is also set.default: false

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", …}]}