Starstruk Logo MarkStarstruk

v0.1.10

jamiepine/voiceboxv0.1.10Jan 30, 2026by github-actions[bot]

AI Summary

Major performance update introducing MLX backend for Apple Silicon, achieving massive speed improvements from ~20s to 2-3s per generation. Added dynamic backend selection between MLX and PyTorch.

Key Highlights

  • Massive speed gains on Apple Silicon (20s to 2-3s per generation)
  • Added native MLX backend support for Apple Silicon
  • Dynamic backend selection (MLX for macOS, PyTorch for other platforms)
  • Refactored TTS and STT into modular backend implementations
  • Platform detection system for runtime backend selection
  • Updated model loading and caching for both backends
  • Enhanced health check to report active backend type
  • Updated build process for MLX-specific dependencies

Breaking Changes

  • Transcriptions broken on Apple Silicon (known issue, patch coming in 0.1.11)

New Features

  • MLX backend for Apple Silicon
  • Dynamic backend selection
  • Platform detection system
  • Modular backend architecture (mlx_backend.py, pytorch_backend.py)
  • MLX-specific requirements (requirements-mlx.txt)
  • MLX documentation and troubleshooting guides

Full Release Notes

## Faster generation on Apple Silicon 

Massive speed gains, from around 20s per generation to 2-3s!

Added native MLX backend support for Apple Silicon, providing significantly faster TTS and STT generation on M-series macOS machines.

**Note: this update broke transcriptions on Apple Silicon only, the patch is in the oven as we speak, 0.1.11 will follow.**

### Features

- **MLX Backend**: New backend implementation optimized for Apple Silicon using MLX framework
- **Dynamic Backend Selection**: Automatically detects platform and selects between MLX (macOS) and PyTorch (other platforms)
- **Improved Performance**: Leverages Apple's unified memory architecture for faster model inference

### Backend Changes

- Refactored TTS and STT logic into modular backend implementations (`mlx_backend.py`, `pytorch_backend.py`)
- Added platform detection system to handle backend selection at runtime
- Updated model loading and caching to support both backend types
- Enhanced health check endpoints to report active backend type

### Build & Release

- Updated build process to include MLX-specific dependencies for macOS builds
- Modified release workflow to handle platform-specific backend bundling
- Added `requirements-mlx.txt` for MLX dependencies

### Documentation

- Updated setup and building guides with MLX-specific instructions
- Added troubleshooting guidance for MLX-related issues
- Enhanced architecture documentation to explain backend selection