All models
expressive

IndexTTS 2

Apache-2.0

Bilibili's TTS with multi-speaker and precise emotion control

IndexTTS 2, from Bilibili, targets professional dubbing: it's the rare autoregressive TTS with explicit duration control (hit an exact clip length) and disentangled emotion control — take the voice from one reference and the emotion from another, or steer it with text.

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 indextts

IndexTTS 2 FAQ

Do I need a GPU to run IndexTTS 2?

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 IndexTTS 2 clone voices?

Yes — IndexTTS 2 supports voice cloning from reference audio.

What license is IndexTTS 2 released under?

IndexTTS 2 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 IndexTTS 2 support?

IndexTTS 2 supports Chinese, English.

Is there a hosted IndexTTS 2 API?

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