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.

Voices

1 voice
Neutral
Defaultdefault
—
NeutralEmotionalNumbers & Dates

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.”

Install

pip install melotts

MeloTTS FAQ

Do I need a GPU to run MeloTTS?

No — MeloTTS runs in real time on a CPU, no GPU required. It's one of the few open TTS models that does.

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?

Yes — OpenSpeech Cloud is launching hosted, pay-per-minute access to MeloTTS and every other model in this directory. No CUDA, Docker, or GPU needed.