Models that read text aloud in natural voices, many of them multilingual and able to run offline.
Ranked by total GitHub stars, refreshed every day.
| # | Repo |
|---|---|
| 1 | Active (pushed in the last 90 days)debpalash/VoiceStudio VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages. 111.9KPython |
| 2 | Active (pushed in the last 90 days)RVC-Boss/GPT-SoVITS 1 min voice data can also be used to train a good TTS model! (few shot voice cloning) 65.2KPython |
| 3 | Inactive (no push for over a year, or archived)coqui-ai/TTS 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production 46.2KPython |
| 4 | Active (pushed in the last 90 days)OpenBMB/VoxCPM VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning 42.6KPython |
| 5 | Slowing down (last push 3–12 months ago)2noise/ChatTTS A generative speech model for daily dialogue. 40KPython |
| 6 | Inactive (no push for over a year, or archived)myshell-ai/OpenVoice Instant voice cloning by MIT and MyShell. Audio foundation model. 38.3KPython |
| 7 | Slowing down (last push 3–12 months ago)babysor/MockingBird 🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time 36.9KPython |
| 8 | |
| 9 | Active (pushed in the last 90 days)mastra-ai/mastra Mastra is the modern TypeScript framework for AI-powered applications and agents. 29.5KTypeScript |
| 10 | Active (pushed in the last 90 days)index-tts/index-tts An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System 25.1KPython |
| 11 | Slowing down (last push 3–12 months ago)QwenAudio/CosyVoice Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability. 24.4KPython |
| 12 | Active (pushed in the last 90 days)DrewThomasson/ebook2audiobook Generate audiobooks from e-books, 50+ TTS engines with voice cloning and 1696 languages! 20.6KPython |
| 13 | Active (pushed in the last 90 days)jianchang512/pyvideotrans Translate the video from one language to another and embed dubbing & subtitles. 19.8KPython |
| 14 | Slowing down (last push 3–12 months ago)nari-labs/dia A TTS model capable of generating ultra-realistic dialogue in one pass. 19.4KPython |
| 15 | Active (pushed in the last 90 days)NVIDIA-NeMo/Speech A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech) 18.8KPython |
| 16 | Inactive (no push for over a year, or archived)supertone-oss-archive/supertonic(archived) Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX. 13.8KSwift |
| 17 | Active (pushed in the last 90 days)huggingface/speech-to-speech Build voice agents with open-source models 13.7KPython |
| 18 | Slowing down (last push 3–12 months ago)abus-aikorea/voice-pro Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation. 13.4KPython |
| 19 | Active (pushed in the last 90 days)rany2/edge-tts Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge 12.6KPython |
| 20 | Active (pushed in the last 90 days)moonshine-ai/moonshine Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces 11.5KC++ |