expressive

StyleTTS 2

MIT code; pretrained voice conditions

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.

Hear StyleTTS 2

StyleTTS 2 · Default · Same three scripts across the directory.

Run it yourself

Best for: Diffusion-based, human-level naturalness on LibriTTS

Commercial conditions: The README requires permission or synthesized-speech disclosure for certain reference voices outside the training set. Its code license is MIT, but the pretrained-model terms must also be followed.

Code: MIT. Weights: Publisher pretrained-model conditions. License sources checked 2026-09-20. Source 1 Source 2 Source 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 →

BarkListen side-by-side →ZonosListen side-by-side →IndexTTS 2Listen side-by-side →

Choose an alternative to hear both models together.

Voices

1 voice

Neutral

Defaultdefault

—

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 StyleTTS 2

pip install styletts2

Sources & setup details

StyleTTS 2 FAQ

Do I need a GPU to run StyleTTS 2?

The directory lists roughly 4 GB of VRAM as a historical estimate. Check the model documentation for your checkpoint and runtime.

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 code; pretrained voice conditions 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?

OpenSpeech Cloud is accepting production-access interest for StyleTTS 2, but this model is not currently hosted in Cloud. Use the official repository for current deployment options.