# F5-TTS

> F5-TTS is a diffusion-transformer (flow matching) text-to-speech model that clones a voice from a reference clip, with a Gradio app, CLI, Docker image and a Triton/TensorRT-LLM deployment path. The code is MIT, but the pre-trained weights are CC-BY-NC-4.0 because of the Emilia training data, so the released models cannot be used commercially. PyTorch runs on NVIDIA, AMD (Linux), Intel GPUs and Apple Silicon. Minimum hardware is not documented.

- Repository: https://github.com/SWivid/F5-TTS
- Official docs: https://github.com/SWivid/F5-TTS#readme
- Checked: 2026-10-15

## What it replaces
- ElevenLabs: Speech generation, Voice cloning (partial). Speech generation and zero-shot voice cloning, but released weights are non-commercial (CC-BY-NC-4.0).
- Descript: Voice cloning, Speech generation (partial). Voice cloning and text-to-speech only; no transcript-based audio or video editing.

## Facts, with sources

| Question | Status | Answer | Source | Checked |
|---|---|---|---|---|
| Runs on my machine? | Confirmed | Yes, local PyTorch on NVIDIA, AMD, Intel GPU or Apple Silicon; Docker image available | https://github.com/SWivid/F5-TTS#installation | 2026-10-15 |
| Code licence | Confirmed | MIT | https://github.com/SWivid/F5-TTS/blob/main/LICENSE | 2026-10-15 |
| Model weights licence | No | CC-BY-NC-4.0 (non-commercial) because of the Emilia training data | https://huggingface.co/SWivid/F5-TTS | 2026-10-15 |
| Commercial use | No | No with the released weights (CC-BY-NC-4.0); the MIT code could be used with your own commercially licensed weights | https://github.com/SWivid/F5-TTS#license | 2026-10-15 |
| Paid services needed? | Confirmed | None required | https://github.com/SWivid/F5-TTS#readme | 2026-10-15 |
| Hardware | Unknown | Not documented; only a benchmark on a single NVIDIA L20 GPU is given | https://github.com/SWivid/F5-TTS#runtime | 2026-10-15 |
| Operating systems | Partial | Linux (AMD ROCm noted as Linux only) and Apple Silicon macOS documented; Windows not mentioned | https://github.com/SWivid/F5-TTS#install-pytorch-with-matched-device | 2026-10-15 |
| Setup effort | Confirmed | Medium, install PyTorch matched to your GPU, FFmpeg, then pip install f5-tts (or Docker) | https://github.com/SWivid/F5-TTS#installation | 2026-10-15 |

GitHub: 15411 stars, 2247 forks, last push 2026-10-14, archived: no.
---
Source: RepoQuarry (https://repoquarry.dev/projects/f5-tts). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.