All models
expressive

StyleTTS 2

MIT

Diffusion-based, human-level naturalness on LibriTTS

StyleTTS 2 made waves by reaching human-level naturalness on standard English benchmarks using style diffusion and adversarial training with large speech-language models. It supports zero-shot speaker adaptation from a short reference clip and remains a favorite for natural prosody.

Voices

1 voice
Neutral
Defaultdefault
—
NeutralEmotionalNumbers & Dates

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.”

Install

pip install styletts2

StyleTTS 2 FAQ

Do I need a GPU to run StyleTTS 2?

For practical speeds, yes — plan on roughly 4 GB of VRAM. If you'd rather not manage a GPU, hosted access to every model in this directory is coming via OpenSpeech Cloud.

Can StyleTTS 2 clone voices?

Yes — StyleTTS 2 supports voice cloning from reference audio.

What license is StyleTTS 2 released under?

StyleTTS 2 is released under the MIT license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does StyleTTS 2 support?

StyleTTS 2 supports English.

Is there a hosted StyleTTS 2 API?

Yes — OpenSpeech Cloud is launching hosted, pay-per-minute access to StyleTTS 2 and every other model in this directory. No CUDA, Docker, or GPU needed.