Open-source text-to-speech
IndexTTS
Clone a speaker while controlling emotion and speaking speed, with multilingual synthesis from a reference recording.
- Voice cloning
- Emotion control
- Speed control
Version & availability
- Project release
- 2.5
- Embedded demo
- 2.5
- Languages
- Chinese, English, Japanese, Spanish and Arabic
IndexTTS 2.5 supersedes the 1.x and 2.0 releases, adding five-language support and speaking-speed control. This embeds the 2.5 demo.
Last checked:
Try IndexTTS
Demo: 2.5 · Official IndexTeam demo
Hosted on Hugging Face. GPU queues, sign-in or usage limits may apply. If the demo does not load here, open it directly using the link above.
License & model terms
Released under the bilibili Model Use License Agreement. See the repository's license for the applicable terms.
Read the project documentation ↗