GET

/v1/schemas/openrouter/audio/audio%2Ftranscriptions?kind=output

kind outputactivity audiohash 1809a719…extracted Sep 30, 2026version currentsource upstream spec ↗

Response body

10 properties · 1 required · 4 $defs
propertytypedescriptionconstraints
text*stringThe transcribed text
confidencenumberProvider confidence for the whole transcript from 0 to 1, present when response_format is verbose_json and the provider scores the full transcriptformat: double
durationnumberDuration of the input audio in seconds, present when response_format is verbose_jsonformat: double
entitiesSTTEntity[]Detected entities with character offsets into text, present when the provider runs entity detection
languagestringDetected or forced language, present when response_format is verbose_json
language_confidencenumberProvider confidence in the detected language from 0 to 1, present when response_format is verbose_json and the provider scores language detectionformat: double
segmentsSTTSegment[]Timestamped transcript segments, present when response_format is verbose_json
taskstringThe task performed, present when response_format is verbose_json
usageSTTUsageAggregated usage statistics for the request
wordsSTTWord[]Timestamped words, present when the provider returns word-level timestamps

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"openrouter","endpointId":"audio/transcriptions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}