f5-tts-mlx and f5-tts-swift
F5-TTS-MLX is a core implementation that F5-TTS-Swift builds upon as a Swift wrapper around MLX, making them complementary tools for different use cases rather than competitors—the Swift version enables iOS/macOS deployment while the MLX version serves as the foundational inference engine.
About f5-tts-mlx
lucasnewman/f5-tts-mlx
Implementation of F5-TTS in MLX
Leverages MLX for efficient inference on Apple Silicon, enabling ~4-second generation on M-series MacBooks through a non-autoregressive flow-matching architecture with diffusion transformers and ConvNeXT v2-based text alignment. Supports zero-shot voice cloning from reference audio, quantized 4-bit and 8-bit model variants for memory-constrained environments, and integrates seamlessly with MLX language models via stdout piping for end-to-end speech synthesis pipelines.
About f5-tts-swift
lucasnewman/f5-tts-swift
Implementation of F5-TTS in Swift using MLX
Scores updated daily from GitHub, PyPI, and npm data. How scores work