Creates a new OpenAI text-to-speech capability adapter.
Owning provider instance used for initialization checks and merged config access.
Initialized OpenAI SDK client.
Synthesizes speech in a single non-streaming request.
Unified TTS request envelope.
Optional_ctx: MultiModalExecutionContextOptional multimodal execution context. Unused directly in this adapter.
Optionalsignal: AbortSignalOptional cancellation signal.
Provider-normalized synthesized audio artifacts.
Streams synthesized speech as incremental audio chunks plus a final full artifact.
Unified TTS request envelope.
Optional_ctx: MultiModalExecutionContextOptional multimodal execution context. Unused directly in this adapter.
Optionalsignal: AbortSignalOptional cancellation signal.
Async generator of audio chunk deltas and a terminal completion chunk.
Adapts OpenAI text-to-speech responses into ProviderPlaneAI's normalized audio artifact surface.
Supports both non-streaming and streaming synthesis using OpenAI's dedicated speech endpoint and normalizes emitted audio into
NormalizedAudio.