IndexTTS-2 / IndexTTS-2.5 (bilibili)
The IndexTTS2 paper (arXiv June 2025) presents duration control as novel for AR TTS; 'first' not independently verified, so not flagged. Weights released 2025-09-08. Commercial use: contact indexspeech@bilibili.com.
- Input
- text, audio
- Output
- audio
- License
- bilibili Model Use License Agreement (commercial use by request)
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Hugging Face | IndexTeam/IndexTTS-2 | huggingface.co/IndexTeam/IndexTTS-2 | — |
| GitHub | — | github.com/index-tts/index-tts | — |
Notable capabilities (2)
- Precise duration control in an autoregressive TTS: Lets users specify the exact number of speech tokens (useful for dubbing/lip-sync) while keeping AR naturalness, and disentangles speaker timbre from emotion (emotion from a separate reference audio or text). source
- IndexTTS-2.5 multilingual (found after launch): 2026-08-10 release adds Japanese, Spanish and Arabic to Chinese/English; speed 0.5-2x, Pinyin/CMU/Kana pronunciation control, RTF ~0.2 on RTX 4090. source