All models
voice-cloning

F5-TTS

MIT (code) · CC-BY-NC-4.0 (weights)

Flow-matching TTS, fast zero-shot voice cloning

F5-TTS uses flow matching with a diffusion transformer to produce fluent, faithful zero-shot voice clones from a single short reference. It became a community favorite for its simple architecture, fast inference, and surprisingly robust cloning quality. The official pretrained weights are CC-BY-NC-4.0 (non-commercial); a community retrain called OpenF5-TTS is Apache-licensed for commercial use.

Hear F5-TTS

F5-TTS · Reference clone · Same three scripts across the directory.

Run it yourself

Best for: Flow-matching TTS, fast zero-shot voice cloning

Noncommercial / separate license: The publisher explicitly limits pretrained weights because of the training-data license. MIT covers code, not commercial use of those weights.

Code: MIT. Weights: CC-BY-NC-4.0. License sources checked 2026-09-20. Source 1Source 2Source 3

Before you choose: Compare the samples with your own use case. Check the linked documentation for code, weight, and voice license terms.

Details awaiting a fresh review. Hardware figures are estimates unless a benchmark is linked.

Compare with similar

Compare all →
OpenVoice v2Listen side-by-side →LlasaListen side-by-side →Chatterbox TurboListen side-by-side →

Choose an alternative to hear both models together.

Voices

1 voice
Female
Reference clonedefault
american

The scripts

Neutral
“The quick brown fox jumps over the lazy dog near the riverbank.”
Emotional
“I can't believe you actually did it. This is incredible!”
Numbers & Dates
“On March 14th, 2025, the team raised $4.2 million at a 38% margin.”

Run F5-TTS

pip install f5-tts

Sources & setup details

F5-TTS FAQ

Do I need a GPU to run F5-TTS?

The directory lists roughly 8 GB of VRAM as a historical estimate. Check the model documentation for your checkpoint and runtime.

Can F5-TTS clone voices?

Yes — F5-TTS supports voice cloning from reference audio.

What license is F5-TTS released under?

F5-TTS is released under the MIT (code) · CC-BY-NC-4.0 (weights) license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does F5-TTS support?

F5-TTS supports English, Chinese.

Is there a hosted F5-TTS API?

OpenSpeech Cloud is accepting production-access interest for F5-TTS, but this model is not currently hosted in Cloud. Use the official repository for current deployment options.