whatmodel.sh / tts / YourTTS
YourTTS
↗ share
+ contribute
YourTTS is an open-weights text-to-speech model from Coqui / Edresson Casanova et al., released December 2021. Licence: cc-by-nc-nd-4.0.
Catalogue identity notes
The released YourTTS checkpoint (github.com/Edresson/YourTTS; Coqui TTS model tts_models/multilingual/multi-dataset/your_tts). The repository states: 'All the released checkpoints are licensed under CC BY-NC-ND 4.0'.
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 YourTTS, out of 148 with a score.
| # | model | score | where |
|---|---|---|---|
| 141 |  MetaVoice 1B v0.1 | 20±3 | local |
| 142 |  Tacotron 2 + HiFi-GAN (VCTK, VITS study) | 19±6 | comparison only |
| 143 | YourTTS | 18±3 | local |
| 144 |  MMS TTS Turkish | 18±4 | local |
| 145 |  Antalia 1 | 17±3 | comparison only |
see all text-to-speech models · find the ones that fit your machine
$ what it's good at
voice cloning▃·▁▁▁▁▁▁▇█▃▃ #37 of 37 * · 22% of its score · 1 test
| test | result | vs the others in its run | counts |
|---|---|---|---|
| ZS-TTS-Evaluation · English zero-shot cloning (DAPS speakers, FLORES+) · Whisper-large-v3 CER lab | 2.9% ✎ | █······█··██ beats 0/3 | 22% |
other tests6 not in a task · 75% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| VoiceCraft zero-shot TTS listening test (80) · naturalness MOS | 2.79 / 5 ✎ | █········█·█ beats 0/2 | 22% |
| LibriSpeech test-clean 4-10 s cross-sentence · HuBERT-large WER | 7.9% ✎ | █···█··█···█ beats 0/3 | 14% |
| ZS-TTS-Evaluation · English zero-shot cloning (DAPS, FLORES+) · ECAPA2 speaker similarity lab | 46.2% ✎ | █····▄·····▄ beats 0/3 | 10% |
| LibriSpeech test-clean 4-10 s cross-sentence · SIM-o (WavLM-TDCNN) | 37.5% ✎ | █··········█ beats 1/3 | 9.5% |
| VoiceCraft zero-shot TTS set (250) · speaker similarity (WavLM-TDCNN) | 41.0% ✎ | █····█·····█ beats 0/2 | 9.4% |
| VoiceCraft zero-shot TTS set (LibriTTS + YouTube, 250) · Whisper medium.en WER | 6.6% ✎ | █······█···█ beats 0/2 | 9.4% |
$ where to run it
Other ways to run it
- Run it as published · needs ~0.42 GB · from github.com/Edresson
uv run --python 3.11 --with coqui-tts --with torch --with torchaudio --with torchcodec tts --text "This is an example!" --model_name tts_models/multilingual/multi-dataset/your_tts --speaker_wav target_speaker_wav.wav --language_idx "en" --out_path speech.wav --device cpu
Weights and documentation: github.com/Edresson ↗
$ how the score was worked out · VoiceCraft: Zero-Shot Speech… 41%, ZS-TTS-Evaluation (Edresson C… 32%, DiTTo-TTS: Diffusion Transfor… 24%
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 |
|---|---|---|
 VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild (arXiv:2403.16973v3) | 3 | 41% |
 ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2 · lab-reported | 2 | 32% |
| DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors (arXiv:2406.11427v2) | 2 | 24% |
| prior · pull toward the middle | 3% | |
| weighted average | = 18.1 |
$ 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