Start real-time speech-to-text on a leg

Language code (e.g. "en", "es")

Emit partial (non-final) transcripts

STT provider: "elevenlabs" (default), "deepgram" (/v1/listen), "deepgram_flux" (/v2/listen, conversational turn detection) or "azure"

API key override (falls back to ELEVENLABS_API_KEY, DEEPGRAM_API_KEY or AZURE_SPEECH_KEY env var depending on provider)

Provider-specific model. Deepgram: default "nova-3". Deepgram Flux: "flux-general-en" (default) or "flux-general-multi".

Deepgram only: milliseconds of silence before a segment is finalized. 0 disables endpointing.

Deepgram only: milliseconds of silence after which an stt.turn event with event=utterance_end is emitted. Deepgram requires interim results for this, which are requested automatically and still suppressed unless partial is true.

Deepgram Flux only: end-of-turn confidence that fires an eager_end_of_turn stt.turn event, enabling speculative generation. Must be between 0.3 and 0.9. When unset, no eager_end_of_turn or turn_resumed events are emitted at all.

Deepgram Flux only: end-of-turn confidence required to close a turn. Deepgram default 0.7.

Deepgram Flux only: milliseconds of silence after which a turn is closed regardless of confidence. Deepgram default 5000.

Instance identifier