Flow-matching TTS with no duration modeling — produces the most natural prosody and sentence rhythm of any local voice model. MIT license. The preferred choice for giving local AI agents a human-sounding voice interface.
This model requires a specialized High-VRAM environment. Ensure you have the latest CUDA Drivers or Metal Framework installed.
Minimum VRAM: 4GB VRAM Recommended
The F5-TTS model by SWivid is a 300M parameter architecture optimized for audio tasks. It requires approximately 2GB of VRAM to comfortably run locally using a FP16 quantization. Extending the context window up to 0 tokens will dynamically allocate further VRAM, meaning high-bandwidth memory hardware is strictly advised.
For running F5-TTS at maximum tokens-per-second, we recommend using LM Studio or Ollama with a GGUF quantization (Q4_K_M or Q6_K). If you are multi-GPU, use vLLM to distribute the layers across your VRAM pool for optimal throughput.
You will need a GPU with at least 4GB of VRAM to run the FP16 quantized version smoothly with a moderate context window.
The simplest method is utilizing Ollama by executing 'ollama run f5-tts' directly in your command line. Alternatively, you can search for the model via LM Studio's interface.