pipecat/changelog/3806.changed.md at cd07937c5dcc413000ede5bbc8a232f477a6cd25

Files

Mark Backman 907ff58d41 Align Ultravox Realtime service with OpenAI/Gemini patterns

- Add InterruptionFrame handling with stop_all_metrics()
- Add processing metrics (start/stop) at response boundaries
- Fix agent transcript handling for voice and text modalities:
  - Voice mode: push LLMTextFrame (append_to_context=False) and
    TTSTextFrame for deltas, skip duplicated final text
  - Text mode: push LLMTextFrame with proper response lifecycle,
    no TTSTextFrame (downstream TTS handles audio)
- Add output_medium parameter to AgentInputParams and OneShotInputParams
- Improve TTFB measurement using VAD speech end time
- Update example with user turn strategies and transcript events
- Add text-only output example (50a-ultravox-realtime-text.py)

2026-02-26 10:44:36 -05:00

274 B

Raw Blame History

Aligned UltravoxRealtimeLLMService frame handling with OpenAI/Gemini realtime services: added InterruptionFrame handling with metrics cleanup, processing metrics at response boundaries, and improved agent transcript handling for both voice and text output modalities.

274 B Raw Blame History

274 B

Raw Blame History