Expand description
Durable, automatic audio transcription.
AudioIngress accepts owned WAV bytes, persists them before returning,
and automatically transcribes them in the background.
Structs§
- Audio
Ingress - Cloneable handle to durable, automatically processed audio.
- Audio
Input - Owned audio and its source metadata.
- Audio
Transcriber - Complete audio transcription pipeline backed by configured provider clients.
- Error
- Error returned by the minimal AudioIngress API.
- Recording
Status - Current state and immutable identity of one recording.
- Status
- Complete current library state.
- Step
Error - Sanitized terminal or retryable step error.
- Step
Status - Current status of one ordered pipeline step.
- Submission
- Result of durably submitting audio.
- Transcription
Job - Cloneable handle for polling one in-memory transcription.
- Transcription
Status - Cheap cloneable snapshot returned by
TranscriptionJob::status.
Enums§
- Error
Kind - Stable library error category.
- JobState
- Overall state of an in-memory transcription job.
- Recording
State - Automatic processing state of one recording.
- Step
- One ordered pipeline operation.
- Step
State - State of one pipeline step.
Constants§
- RECONCILIATION_
MODEL - Codex model used to reconcile ordered chunk transcripts.
- RECONCILIATION_
REASONING - Codex reasoning setting used for transcript reconciliation.
- TRANSCRIPTION_
MODEL - Gemini model used for chunk transcription.