x-cpod-domain: stt
Speech-to-Text
Audio-to-text via cpod-backend, which forwards to coreiq's governed gateway. Multipart upload; returns OpenAI-compatible {text, _meta} shape.
Try in explorer
client.sttTranscription
Speech-to-text transcription request and response.
REST path
client.sttOperations
transcribeSDK
// list — returns only your records; add filters/search:
await client.stt.list()| Field | Type | Description |
|---|---|---|
| file* | file | Audio bytes (Blob or File). MIME type inferred from `audio.type`. |
| language | string | BCP-47 language hint (e.g. 'en', 'pt-BR'). Omit for auto-detect. |
| model | string | Provider model id. Common values: google/gemini-2.5-flash, openai/gpt-audio, mistralai/voxtral-small-24b-2507. |
| metadata | json | Opaque passthrough dict echoed on coreiq's trace row. |