I've been working on *vibevoice-rs*, a Rust implementation of VibeVoice for text-to-speech with voice cloning and multi-speaker synthesis. The project brings TTS capabilities to the Rust ecosystem with a focus on performance and flexibility.
What it does:
- Text-to-speech synthesis with voice cloning support
- Multi-speaker synthesis for varied voice output
- Built entirely in Rust for performance and safety
- Designed to be embeddable in other Rust projects
Current status:
This is an early-stage project that I'm actively developing. If you're interested in TTS, voice synthesis, or Rust audio processing, I'd love to hear your thoughts and feedback.
I've been working on *vibevoice-rs*, a Rust implementation of VibeVoice for text-to-speech with voice cloning and multi-speaker synthesis. The project brings TTS capabilities to the Rust ecosystem with a focus on performance and flexibility.
What it does:
- Text-to-speech synthesis with voice cloning support - Multi-speaker synthesis for varied voice output - Built entirely in Rust for performance and safety - Designed to be embeddable in other Rust projects
Current status:
This is an early-stage project that I'm actively developing. If you're interested in TTS, voice synthesis, or Rust audio processing, I'd love to hear your thoughts and feedback.
Repository: https://github.com/danielclough/vibevoice-rs
I'm particularly interested in:
- Performance optimization suggestions - Use cases you'd find valuable - Contributions from anyone interested in audio ML or Rust systems programming