lucasnewman/f5-tts-mlx
Non-autoregressive zero-shot TTS with MLX
View on index · View in 3D Map
Related repos
- Model for singing voice synthesis with zero-shot capabilities
- LLM for voice interactions without ASR stage
- Native Apple Silicon MLX port of Karpathy’s autoresearch
- Generative image models in native MLX for Mac
- Realtime TTS without GPU
- Controls video motion without training
- TTS, STT, and STS on Apple Silicon
- Text-to-speech for Apple Silicon using MLX
- AI text-to-speech tool with fast voice cloning and emotion
- LLM training framework for Apple Silicon
