v0.55.0 v0.55.1
QwenLM/Qwen-MM-PluginsOct 2, 2026 → Oct 2, 20260 days between releases
What's New
Switched default TTS to Deepgram Aura for speed and fixed pause-mode barge-in audio drop bug.
New Features
- Added `BOT_TTS_MODEL` configuration option for OpenAI TTS provider.
Improvements
- Default TTS provider changed to Deepgram Aura for faster response times.
- Improved PSTN call latency between caller and bot.
Bug Fixes
- Fixed pause-mode barge-in dropping bot audio after arbitration resolution.
Upgrade Notes
The default TTS provider changed to Deepgram Aura; set `BOT_TTS_PROVIDER=openai` if you need OpenAI. The new `BOT_TTS_MODEL` setting is now available for the OpenAI provider.
The Two Releases
v0.55.0
Oct 2, 2026· 20 days ago
Introduces a new Pipecat transport (`siphon-ai-pipecat`) to integrate with Pipecat pipelines, ensuring real-time audio pacing and better handling of interruptions, along with a security update to Sightglass.
Full release notesv0.55.1
Oct 2, 2026· 20 days ago
Updates the default Text-to-Speech (TTS) provider in the pipecat-bot-py example to Deepgram Aura for significantly faster response times, and fixes a pause-mode barge-in bug where bot audio was dropped after resolution.
Full release notes