Retrieve speech-to-text history item
Returns metadata for a stored transcription.
Authorizations
Gateway auth: send Authorization: Bearer <mka1-api-key>. For multi-user server-side integrations, you can also send X-On-Behalf-Of: <external-user-id>.
Headers
Optional external end-user identifier forwarded by the API gateway.
Path Parameters
Response
OK
A stored speech-to-text transcription.
Unique identifier for the history item.
The object type, always 'speech.transcription'.
The transcribed text.
The detected or specified language code.
Confidence score from 0 to 1, when available.
The transcription model used.
The provider that produced the transcription.
Original filename of the input audio, when available.
Size of the input audio in bytes.
-9007199254740991 <= x <= 9007199254740991MIME type of the stored input audio.
Speaker diarization segments, when present.
Whether the transcription came from the streaming WebSocket.
Arbitrary metadata stored with the item.
Unix timestamp (seconds) when the item was created.
-9007199254740991 <= x <= 9007199254740991