Files
pipecat/changelog/3132.changed.md
2025-12-05 11:35:49 -05:00

2 lines
380 B
Markdown

- Improved interruption handling to prevent bots from repeating themselves. LLM services that return multiple sentences in a single response (e.g., `GoogleLLMService`) are now split into individual sentences before being sent to TTS. This ensures interruptions occur at sentence boundaries, preventing the bot from repeating content after being interrupted during long responses.