myshell-ai/MeloTTS

Python

High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.

text-to-speechttschineseenglishfrenchjapanesekoreanmultilingualspanish
Star Growth
Stars
7.6k
Forks
1.1k
Weekly Growth
+11
Issues
213
2k4k6k
Feb 2024Dec 2024Oct 2025Sep 2026
ArtifactsPyPI
README
 

myshell-ai%2FMeloTTS | Trendshift

Introduction

MeloTTS is a high-quality multi-lingual text-to-speech library by MIT and MyShell.ai. Supported languages include:

Language Example
English (American) Link
English (British) Link
English (Indian) Link
English (Australian) Link
English (Default) Link
Spanish Link
French Link
Chinese (mix EN) Link
Japanese Link
Korean Link

Some other features include:

  • The Chinese speaker supports mixed Chinese and English.
  • Fast enough for CPU real-time inference.

Usage

The Python API and model cards can be found in this repo or on HuggingFace.

Contributing

If you find this work useful, please consider contributing to this repo.

  • Many thanks to @fakerybakery for adding the Web UI and CLI part.

Authors

Citation

@software{zhao2024melo,
  author={Zhao, Wenliang and Yu, Xumin and Qin, Zengyi},
  title = {MeloTTS: High-quality Multi-lingual Multi-accent Text-to-Speech},
  url = {https://github.com/myshell-ai/MeloTTS},
  year = {2023}
}

License

This library is under MIT License, which means it is free for both commercial and non-commercial use.

Acknowledgements

This implementation is based on TTS, VITS, VITS2 and Bert-VITS2. We appreciate their awesome work.

Related repositories
harry0703/MoneyPrinterTurbo

利用 AI 大模型和自动化工作流,根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

PythonPyPIMIT Licensepythontiktok
121.6k18.8k
unslothai/unsloth

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

PythonPyPIApache License 2.0fine-tuningllama
unsloth.ai/docs
75.9k6.9k
RVC-Boss/GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

PythonPyPIMIT Licensetext-to-speechtts
61.6k6.6k
calesthio/OpenMontage

World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.

PythonPyPIGNU Affero General Public License v3.0agentagentic-ai
openmontage.video
56.7k7.1k
coqui-ai/TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

PythonPyPIMozilla Public License 2.0pythontext-to-speech
coqui.ai
46k6.1k
2noise/ChatTTS

A generative speech model for daily dialogue.

PythonPyPIGNU Affero General Public License v3.0agenttext-to-speech
2noise.com
39.8k4.2k
myshell-ai/OpenVoice

Instant voice cloning by MIT and MyShell. Audio foundation model.

PythonPyPIMIT Licensetext-to-speechtts
research.myshell.ai/open-voice
37.5k4.2k
babysor/MockingBird

🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

PythonPyPIOtheraispeech
36.9k5.2k
OpenBMB/VoxCPM

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

PythonPyPIApache License 2.0audiodeeplearning
voxcpm.com
36.9k4.2k
index-tts/index-tts

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

PythonPyPIOtherbigvgancross-lingual
23.8k2.9k
QwenAudio/CosyVoice

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

PythonPyPIApache License 2.0audio-generationgpt-4o
funaudiollm.github.io/cosyvoice3
23.5k2.7k
debpalash/VoiceStudio

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

PythonPyPIGNU Affero General Public License v3.0ttsvoice-cloning
voicestudio.sh
21.4k2.7k