whatmodel.sh / tts / OpenVoice V1
OpenVoice V1
↗ share
+ contribute
OpenVoice V1 is an open-weights text-to-speech model from MyShell, released January 2024. Licence: mit.
Catalogue identity notes
myshell-ai/OpenVoice (V1). Distinct from OpenVoice V2 (myshell-ai/OpenVoiceV2, MeloTTS base speakers).
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 OpenVoice V1, out of 148 with a score, then more from MyShell.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 77 |  Llasa-8B | 52±3 | local | ||
| 78 |  Gradium TTS | 51±3 | api $38.00/M chars | ||
| 79 | OpenVoice V1 | 51±14 | local | ||
| 80 |  Eleven Multilingual v2 | 51±5 | api $100.00/M chars | ||
| 81 |  Azure Ameha Neural | 50±16 | comparison only | ||
| more from MyShell | |||||
| 103 | MeloTTS English | 44±5 | local | ||
| 138 | OpenVoice V2 | 26±3 | local | ||
see all text-to-speech models · find the ones that fit your machine
$ what it's good at
other tests1 not in a task · 16% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| TTSDS v1 · default four-factor score | 87.1% ✎ | ▂▂····▃·▃▅▂█ beats 10/14 | 16% |
$ where to run it
Other ways to run it
- Run it as published · needs ~0.3 GB · from github.com/myshell-ai
conda create -n openvoice python=3.9 && conda activate openvoice && git clone https://github.com/myshell-ai/OpenVoice.git && cd OpenVoice && pip install -e . && huggingface-cli download myshell-ai/OpenVoice --revision c70fc8b939bd1d8213994ff7c88e32be39708271 --include 'checkpoints/*' --local-dir . && python -c "import os, torch from openvoice import se_extractor from openvoice.api import BaseSpeakerTTS, ToneColorConverter ckpt_base = 'checkpoints/base_speakers/EN' ckpt_converter = 'checkpoints/converter' device='cuda:0' if torch.cuda.is_available() else 'cpu' output_dir = 'outputs' base_speaker_tts = BaseSpeakerTTS(f'{ckpt_base}/config.json', device=device) base_speaker_tts.load_ckpt(f'{ckpt_base}/checkpoint.pth') tone_color_converter = ToneColorConverter(f'{ckpt_converter}/config.json', device=device) tone_color_converter.load_ckpt(f'{ckpt_converter}/checkpoint.pth') os.makedirs(output_dir, exist_ok=True) source_se = torch.load(f'{ckpt_base}/en_default_se.pth').to(device) reference_speaker = 'resources/example_reference.mp3' target_se, audio_name = se_extractor.get_se(reference_speaker, tone_color_converter, target_dir='processed', vad=True) save_path = f'{output_dir}/output_en_default.wav' text = 'This audio is generated by OpenVoice.' src_path = f'{output_dir}/tmp.wav' base_speaker_tts.tts(text, src_path, speaker='default', language='English', speed=1.0) tone_color_converter.convert(audio_src_path=src_path, src_se=source_se, tgt_se=target_se, output_path=save_path, message='@MyShell') "
Weights and documentation: huggingface.co/myshell-ai ↗
$ how the score was worked out · TTSDS v1 published results 16%
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 |
|---|---|---|
 TTSDS v1 published results | 1 | 16% |
| prior · pull toward the middle | 84% | |
| weighted average | = 50.7 |
$ 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