All models
lightweight

MeloTTS

MIT

Multilingual, real-time on CPU

MeloTTS from MyShell.ai is one of the most-downloaded open TTS models on Hugging Face. It covers English (with multiple accents), Spanish, French, Chinese, Japanese and Korean, and was designed for real-time inference even on CPU. A clean, dependable choice for multilingual products.

Hear MeloTTS

MeloTTS · Default · Same three scripts across the directory.

Run it yourself

Best for: Multilingual, real-time on CPU

Permissive model license: Official code and the English checkpoint explicitly allow commercial use under MIT. Other language checkpoints and phonemizer dependencies need their own notice handling.

Code: MIT. Weights: MIT (MeloTTS-English). License sources checked 2026-09-20. Source 1Source 2Source 3

Before you choose: Compare the samples with your own use case. Check the linked documentation for code, weight, and voice license terms.

Details awaiting a fresh review. Hardware figures are estimates unless a benchmark is linked.

Compare with similar

Compare all →
Kokoro-82MListen side-by-side →PiperListen side-by-side →KittenTTSListen side-by-side →

Choose an alternative to hear both models together.

Voices

1 voice
Neutral
Defaultdefault
—

The scripts

Neutral
“The quick brown fox jumps over the lazy dog near the riverbank.”
Emotional
“I can't believe you actually did it. This is incredible!”
Numbers & Dates
“On March 14th, 2025, the team raised $4.2 million at a 38% margin.”

Run MeloTTS

pip install melotts

Sources & setup details

MeloTTS FAQ

Do I need a GPU to run MeloTTS?

MeloTTS supports CPU inference. Speed depends on your processor, runtime, and text.

Can MeloTTS clone voices?

No — MeloTTS uses preset voices. Browse the voice-cloning category for models that clone from reference audio.

What license is MeloTTS released under?

MeloTTS is released under the MIT license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does MeloTTS support?

MeloTTS supports English, Spanish, French, Chinese, Japanese, Korean.

Is there a hosted MeloTTS API?

OpenSpeech Cloud is accepting production-access interest for MeloTTS, but this model is not currently hosted in Cloud. Use the official repository for current deployment options.