- Home
- Text-to-speech tools
- IndexTTS
IndexTTS
What it is
IndexTTS is a free, open-source text-to-speech system that creates speech by cloning a voice from a single reference audio clip. IndexTTS-2.5 supports Chinese, English, Japanese, Spanish, and Arabic, with WAV output. Speaking speed can be adjusted with duration_factor values from 0.5 to 2.0, where 1.0 is normal speed. Pronunciation controls include Chinese Pinyin, English CMU phonemes, and Japanese Kana; for IndexTTS-2, Pinyin control applies only to supported cases in the project's vocabulary file. Emotion can be guided by a reference recording, an emotion vector, or text. The project provides a browser-based WebUI and a Python API, and documents a vLLM recipe for production serving. Setup instructions cover Windows and Linux, model downloads through Hugging Face or ModelScope, and use of Git and uv. CUDA Toolkit 12.8 or newer is recommended for CUDA installation errors on either operating system. DeepSpeed is optional, and its effect depends on hardware, drivers, and operating system. IndexTTS is released under the bilibili Model Use License Agreement, and the project asks users to read its disclaimer. Commercial users are directed to contact [email protected].
For and against
For
- Clones a voice from one reference audio clip.
- Supports five languages in IndexTTS-2.5.
- Offers emotion and speaking-speed controls.
- Provides a WebUI and Python API.
Against
- Pinyin control for IndexTTS-2 covers only listed supported cases.
- Setup instructions call for Git and uv.
- Commercial use requires contacting the project.
The verdict
IndexTTS offers local interfaces, voice cloning, pronunciation controls, and several ways to guide emotion. Users should review the license and disclaimer, and account for the setup requirements before choosing it.
Who it suits
IndexTTS suits developers and other users who want to run voice-cloning text-to-speech through a WebUI or Python API. It may also fit users who can work with its setup requirements and license terms.
Plans and prices
IndexTTS
No hosted plan or price listed; downloadable model and inference code
Read 9 Oct 2026 · github.com
On the record
- Acceleration
- Optional DeepSpeed support may speed up inference on some systems, but the repository says results depend on hardware, drivers, and operating system.github.com · read 9 Oct 2026
- API access
- Yesgithub.com · read 20 Sep 2026
- Commercial use
- For commercial usage and cooperation, the project directs users to contact [email protected].github.com · read 9 Oct 2026
- Deployment
- The project documents a local WebUI, a Python API, and production serving through a vLLM recipe.github.com · read 9 Oct 2026
- Emotion control
- Speech emotion can be controlled with an emotional reference recording, an emotion vector, or text.github.com · read 9 Oct 2026
- Export formats
- WAVgithub.com · read 20 Sep 2026
- Hardware
- The README recommends NVIDIA CUDA Toolkit 12.8 or newer on Linux or Windows when a CUDA installation error occurs.github.com · read 9 Oct 2026
- Installation platforms
- The README gives installation guidance for Windows and Linux and notes that DeepSpeed may be difficult to install on Windows.github.com · read 9 Oct 2026
- Interfaces
- The repository provides a browser-based WebUI and a Python API for inference.github.com · read 9 Oct 2026
- Languages
- IndexTTS-2.5 supports Chinese, English, Japanese, Spanish, and Arabic.github.com · read 9 Oct 2026
- License
- The project says it is released under the bilibili Model Use License Agreement and asks users to read its disclaimer before use.github.com · read 9 Oct 2026
- Model downloads
- The README provides model download instructions using Hugging Face or ModelScope.github.com · read 9 Oct 2026
- Notable pronunciation limit
- For IndexTTS-2, Pinyin control works only for supported Chinese Pinyin cases listed in the project's vocabulary file.github.com · read 9 Oct 2026
- Official channel
- The maintainers identify the GitHub repository as the only official channel maintained by the core team and say other sites or services are not official.github.com · read 9 Oct 2026
- Official channel and security
- The maintainers say the GitHub repository is their only official channel and that they cannot guarantee the security, accuracy, or timeliness of other websites or services.github.com · read 9 Oct 2026
- Product
- IndexTTS is a zero-shot text-to-speech system that clones a voice from a single reference audio clip.github.com · read 9 Oct 2026
- Pronunciation
- IndexTTS-2.5 supports pronunciation control using Chinese Pinyin, English CMU phonemes, and Japanese Kana.github.com · read 9 Oct 2026
- Purpose
- IndexTTS is a zero-shot text-to-speech system that clones a voice from a single reference audio clip.github.com · read 9 Oct 2026
