All models
expressive

MegaTTS 3

Apache-2.0

ByteDance's TTS with sparse alignment — robust prosody

MegaTTS 3 is ByteDance's open release: a compact 0.45B diffusion-transformer TTS with high-quality zero-shot cloning, bilingual Chinese/English support with code-switching, and unusual extras like adjustable accent intensity for pronunciation control.

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 megatts3

MegaTTS 3 FAQ

Do I need a GPU to run MegaTTS 3?

For practical speeds, yes — plan on roughly 8 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 MegaTTS 3 clone voices?

Yes — MegaTTS 3 supports voice cloning from reference audio.

What license is MegaTTS 3 released under?

MegaTTS 3 is released under the Apache-2.0 license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does MegaTTS 3 support?

MegaTTS 3 supports Chinese, English.

Is there a hosted MegaTTS 3 API?

Yes — OpenSpeech Cloud is launching hosted, pay-per-minute access to MegaTTS 3 and every other model in this directory. No CUDA, Docker, or GPU needed.