v0.7.2

parruda/swarmv0.7.2May 25, 2026by KoljaB

AI Summary

This update reworks the PocketTTS engine to run synthesis through a persistent worker thread. It adds streaming controls, custom model configs, and voice state caching to improve performance and flexibility.

Key Highlights

Reworked PocketTTS engine to use persistent worker thread.
Added streaming controls (streaming, max_tokens).
Added support for custom model configs.

New Features

Persistent worker thread for synthesis
Streaming controls and max_tokens
Custom model configuration support

Full Release Notes

# RealtimeTTS v0.7.2

### Improvements

* Reworked `PocketTTSEngine` to run synthesis through a persistent worker thread.
* Patched PocketTTS short-text streaming to decode serially, avoiding Windows/Torch CPU memory retention during repeated short generations.
* Added PocketTTS streaming controls: `streaming`, `max_tokens`, and `frames_after_eos`.
* Added support for custom PocketTTS model configs via `model_config`.
* Added support for cached voice states through `PocketTTSVoice(state_path=...)`.
* Added optional voice-state caching through `voice_cache_dir` and `cache_voice_states`.
* Improved PocketTTS audio conversion, queueing, duration tracking, and shutdown cleanup.

### Packaging

* Bumped package version to `0.7.2`.
* Set the PocketTTS dependency to `pocket-tts>=2.1.0`.
* Refreshed explicit dependency versions, including `stream2sentence`, `openai`, `elevenlabs`, `edge-tts`, `requests`, `cartesia`, `camb-sdk`, `omnivoice`, and `typecast-python`.

### Documentation

* Added PocketTTS runtime notes for the persistent worker and serial streaming behavior.
* Cleaned up the README support section.