GET
/v1/schemas/byteplus/audio/auc/bigmodel/recognize/flash?kind=output
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. docs-derived Source traceebffeaf934197130d6b4cc6534a33b6b04d51a5a71ce2403b2bcf8c7e2cb627f{
"fetchedAt": 1786770726,
"extractorVersion": "1",
"verifiedAt": null
} |
Response body
4 properties · 0 required · 1 $defs| property | type | description | constraints |
|---|---|---|---|
| audio_info | object | ||
| result | object | ||
| transcript | string | Flat alias for result.text. | |
| utterances | ASRUtterance[] |
Types
1 $defsASRUtteranceobject
One recognised utterance; start_time/end_time are milliseconds.
| text | string | ||
| start_time | number | ||
| end_time | number | ||
| words | object[] | ||
| additions | object | Extra per-utterance annotations; speaker labels arrive here when enable_speaker_info is set. |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"byteplus","endpointId":"auc/bigmodel/recognize/flash","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}