v0.7.3

KoljaB/RealtimeTTSv0.7.3May 25, 2026by KoljaB

AI Summary

This release introduces GPU support for PocketTTS via a new `PocketTTSGpuEngine` and `PocketTTSGpuVoice`. It also refines core engine usability with explicit device support, lazy exports, and improved silence trimming.

Key Highlights

  • Added `PocketTTSGpuEngine` and `PocketTTSGpuVoice` for CUDA-capable setups.
  • Added explicit `device` support to `PocketTTSEngine` for CPU users.
  • Delayed `stream2sentence` tokenizer initialization to reduce import overhead.
  • Added `pockettts-gpu` and `pocket-gpu` extras for GPU dependencies.

New Features

  • PocketTTS GPU engine with built-in voice support and silence trimming.
  • Lazy root exports for the new GPU engine.
  • Cached prompt state loading and saving for the GPU engine.
  • Optional silence trimming for the GPU engine.

Full Release Notes

# RealtimeTTS v0.7.3

### Features

* PocketTTS GPU
  * Added `PocketTTSGpuEngine` and `PocketTTSGpuVoice` for the CUDA-capable `pocket-tts-gpu` fork.
  * Added built-in voice support, prompt WAV voice cloning, cached prompt state loading/saving, and optional silence trimming for the GPU engine.
  * Added lazy root exports and `RealtimeTTS.engines` exports for the new GPU engine.

### Improvements

* PocketTTS
  * Added explicit `device` support to `PocketTTSEngine` so CPU users can stay on CPU while advanced users can move the official PocketTTS model to another Torch device.
  * Kept CPU and GPU PocketTTS paths separate so normal `realtimetts[pockettts]` installs remain predictable.
* Import Behavior
  * Delayed `stream2sentence` tokenizer initialization until sentence generation is actually used, keeping `import RealtimeTTS` quieter and lighter.
* Packaging
  * Bumped the package version to `0.7.3`.
  * Added `pockettts-gpu` and `pocket-gpu` extras for the shared GPU-engine dependencies.

### Fixes

* Avoided import-time tokenizer setup from `TextToAudioStream`, which could surprise users before they created or played a stream.
* Improved the missing-dependency message for `PocketTTSGpuEngine` with the pinned GPU fork install command.

### Documentation

* Expanded PocketTTS documentation with separate CPU and CUDA fork installation paths.
* Documented CUDA PyTorch installation and the pinned PocketTTS GPU fork revision used for this release.
* Updated installation and engine-selection docs to list `PocketTTSGpuEngine` and the new GPU extras.
* Updated the README engine matrix to show the optional PocketTTS GPU path.

### Tests and Examples

* Added unit coverage for `PocketTTSGpuEngine` streaming output and `PocketTTSGpuVoice` representation.
* Expanded PocketTTS tests around device forwarding.
* Verified the PyPI wheel and source distribution with `twine check`.
* Smoke-tested the built wheel by installing it and importing `PocketTTSGpuEngine` / `PocketTTSGpuVoice`.

### Notes

* PyPI release: `pip install realtimetts==0.7.3`
* CPU PocketTTS install: `pip install "realtimetts[pockettts]"`
* GPU PocketTTS install starts with `pip install "realtimetts[pockettts-gpu]"`, then requires a CUDA-enabled PyTorch build and the pinned `pocket-tts-gpu` fork documented in `docs/engines/pockettts.md`.
* No intentional breaking changes.