Wyoming Openai – Streaming hotfix and Chatterbox TTS release (0.3.8)
🎙️ Wyoming OpenAI 0.3.8 is live—and TTS streaming just got a serious upgrade!
Say goodbye to stilted audio pauses. The new smart TTS streaming uses pySBD to chunk text at sentence boundaries, then prefetches the next line while playing the current one—so even if OpenAI stumbles, your voice assistant keeps flowing.
🚀 Highlights:
- 🚀 Parallel prefetching: Up to 3 TTS requests running at once, sequenced perfectly.
- 🐳 Chatterbox TTS support: Drop-in Docker compose for self-hosted neural voices—with voice cloning!
- 🛡️ Robust error handling: New `TtsStreamError` + `_abort_synthesis` to kill broken streams and stop audio doubles.
- 📦 Install via `pip install wyoming-openai`—no git needed.
- 🔧 Updated deps: `openai==2.3.0`, `wyoming==1.8.0` for full compatibility.
Perfect for Home Assistant users who want smooth, low-latency voice—whether on cloud APIs or local models like Piper, Kokoro, or Edge TTS.
No more buffering. Just natural, uninterrupted speech. 🎧✨
Check the docs and start streaming!