Creates a new Gemini audio transcription capability adapter.
Owning provider instance used for initialization checks and merged config access.
Initialized Google GenAI SDK client.
Transcribes audio in non-streaming mode.
Steps:
generateContent and normalize outputUnified transcription request envelope.
Optional multimodal execution context. Unused directly in this adapter.
Optionalsignal: AbortSignalOptional cancellation signal.
Provider-normalized transcript artifacts.
Transcribes audio in streaming mode and emits incremental transcript deltas.
Emits:
done: false chunks while transcript text accumulatesdone: true completed chunkdone: true error chunk on failureUnified transcription request envelope.
Optional multimodal execution context. Unused directly in this adapter.
Optionalsignal: AbortSignalOptional cancellation signal.
Async generator of delta and final transcript chunks.
Adapts Gemini audio transcription responses into ProviderPlaneAI's normalized chat artifact surface.
Supports non-streaming and streaming transcription by sending audio plus an instruction prompt through Gemini multimodal content generation APIs.