whatmodel.sh / tts / IndexTTS (v1)
IndexTTS (v1)
↗ share
+ contribute
IndexTTS (v1) is an open-weights text-to-speech model from IndexTeam (bilibili), released March 2025. Licence: bilibili-model-use-license.
Catalogue identity notes
IndexTeam/Index-TTS, the first release. Distinct from IndexTTS-1.5 and IndexTTS-2 (existing id indextts-2). HF card metadata says apache-2.0, while the index-tts repository is released under the bilibili Model Use License Agreement.
Score within the Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot comparison set only.
$ how it compares
The text-to-speech models ranked either side of IndexTTS (v1), out of 148 with a score, then more from IndexTeam (bilibili).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 37 |  Fish Audio S2 Pro | 63±1 | api $15.00/M chars +local | ||
| 38 |  Eleven Flash v2.5 | 63±2 | api $50.00/M chars | ||
| 39 | IndexTTS (v1) | 62±3 | local | ||
| 40 |  F5-TTS v1 Base | 62±3 | local | ||
| 41 |  Inworld TTS-1.5 Max | 62±3 | api $10.00/M chars | ||
| more from IndexTeam (bilibili) | |||||
| 32 | IndexTTS-2 | 63±1 | local | ||
see all text-to-speech models · find the ones that fit your machine
$ what it's good at
voice cloning▁·▁▁▁▁▁▁▇█▃▃ #12 of 37 · 41% of its score · 3 tests
Beats Gemini 3.1 Flash TTS Preview, VoxCPM 0.5B, Fun-CosyVoice3-0.5B-2512 here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Seed-TTS test-en · speaker similarity (WavLM-large SV) | 61.0% ✎ | ▁·▂▃▂█▆▃▅··▂ beats 4/30 | 21% |
| Seed-TTS test-en · UTMOS (predicted MOS) | 3.98 / 5 ✎ | ▄█▄··▄···▄·▄ beats 6/6 | 11% |
| Seed-TTS test-en · Whisper large-v3 WER | 1.9% ✎ | ▁···▂▂▂▂█▆▄▂ beats 15/35 | 10% |
other tests3 not in a task · 55% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LibriSpeech-PC test-clean (F5-TTS subset) · speaker similarity (WavLM SV) | 62.0% ✎ | ▄······▄·█▄▄ beats 1/5 | 24% |
| LibriSpeech-PC test-clean (F5-TTS subset) · UTMOS (predicted MOS) | 4.35 / 5 ✎ | █···█······█ beats 2/2 | 15% |
| LibriSpeech-PC test-clean (F5-TTS 4-10 s subset) · Whisper large-v3 WER | 2.6% ✎ | █····████··█ beats 3/5 | 15% |
$ where to run it
Other ways to run it
- Run it as published · needs ~1.22 GB · from github.com/index-tts
git clone https://github.com/index-tts/index-tts.git && cd index-tts && git checkout 8d2759b2b73b920e58ccc0167fc2a445fb170860 && pip install -r requirements.txt && huggingface-cli download IndexTeam/Index-TTS bigvgan_discriminator.pth bigvgan_generator.pth bpe.model dvae.pth gpt.pth unigram_12000.vocab --local-dir checkpoints && pip install -e . && indextts "大家好，我现在正在bilibili 体验 ai 科技，说实话，来之前我绝对想不到！AI技术已经发展到这样匪夷所思的地步了！" --voice reference_voice.wav --model_dir checkpoints --config checkpoints/config.yaml --output output.wav
Official weights and documentation: huggingface.co/IndexTeam ↗
$ how the score was worked out · DiSTAR: Diffusion over a Scal… 96%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation (arXiv:2510.12210v2) | 6 | 96% |
| prior · pull toward the middle | 4% | |
| weighted average | = 62.2 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json