whatmodel.sh / tts / MeloTTS English

MeloTTS English

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

MeloTTS English is an open-weights text-to-speech model from MyShell, released February 2024. Licence: mit.

Catalogue identity notes

myshell-ai/MeloTTS-English, the checkpoint MeloTTS loads for language 'EN' (download_utils.py maps EN to this repo; EN_V2 and EN_NEWEST are separate checkpoints). Fixed-voice multi-accent English VITS2-based model. Code and weights MIT.

43.9±4.5#81 of 118 text-to-speech modelsfrom 3 benchmark results across 2 sources

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 MeloTTS English, out of 148 with a score, then more from MyShell.

#modelscorewhereRAMreleased
101KittenTTS Nano 0.8 KittenML44±5comparison only2026-02
102GPT-SoVITS v2 RVC-Boss44±4local~1.1GB2024-08
103MeloTTS English MyShell44±5local~0.7GB2024-02
104Parler-TTS Mini v1 Hugging Face (Parler-TTS)44±6local~3.5GB2024-08
105Sonic (1) Cartesia42±3comparison only2024-05
more from MyShell
79OpenVoice V1 MyShell51±14local~0.3GB2024-01
138OpenVoice V2 MyShell26±3local~0.8GB2024-04

see all text-to-speech models · find the ones that fit your machine

$ what it's good at

other tests3 not in a task · 92% of its score
testresultvs the others in its rundifficultycountswhy
VERSA TTS demo · LibriSpeech test-clean UTMOS3.80 / 5 ✎▄·····▄·▄█·▄ beats 3/5easy · avg 4.11 / 5▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 45%at its level
DailyDialog TTS · Whisper-large WER (UncovAI deepfake study)6.4% ✎▄··········█ beats 2/2avg 4.3%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 45%small run
VERSA TTS demo · LibriSpeech test-clean Whisper WER4.6% ✎▄··········█ beats 4/5avg 6.4%▇ 1.4%blunt · noisy

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~0.65 GB · from github.com/myshell-ai
    git clone https://github.com/myshell-ai/MeloTTS.git && cd MeloTTS && pip install -e . && python -m unidic download && melo "Text to read" output.wav

Weights and documentation: huggingface.co/myshell-ai ↗

$ how the score was worked out · VERSA toolkit paper: TTS demo… 47%, Audio Deepfake Detection in t… 45%

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

sourceresultsshare of the scorelicence
VERSA toolkit paper: TTS demonstration (arXiv:2412.17667v2)2▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 47%CC BY 4.0
Audio Deepfake Detection in the Age of Advanced Text-to-Speech models (arXiv:2601.20510v1)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 45%CC BY 4.0
prior · pull toward the middle▇▇ 8%
weighted average= 43.9

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

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