Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
List of all local & free open-source voice-clone TTS models and music generation models.
| Date | Stars |
|---|---|
| 2026-07-31 | 435 |
| 2026-08-06 | 538 |
Today
+103 stars today
This week
— stars this week
This month
— stars this month
Momentum
362.0
growth rate 0.00%/day
# local & free open-source voice-clone TTS models and music generation models. ---  ## Table of Contents - [Text-to-Speech (TTS) Models](#text-to-speech-tts-models) - [Music Generation Models](#music-generation-models) - [Anything to Audio](#anything-to-audio) - [Audio Restoration & Enhancement](#audio-restoration--enhancement) - [Speech Recognition (ASR)](#speech-recognition-asr) - [Additional Resources](#additional-resources) --- ## Text-to-Speech (TTS) Models ### TTS Quick Comparison | Model | Voice Cloning | ASR | Languages | Streaming | License | | :--- | :---: | :---: | :--- | :---: | :--- | | [Voxtral-4B-TTS-2603](#Voxtral-4B-TTS-2603) | ✔️ | ✔️ | 50+ | ✔️ | Apache-2.0 | | [LongCat-AudioDiT](#longcat-audiodit) | ✔️ | ❌ | Zh/En | ❌ | MIT | | [Fish Audio S2 Pro](#fish-audio-s2-pro) | ✔️ | ❌ | 80+ | ✔️ | Research License | | [KittenTTS](#kittenTTS) | ✔️ | ❌ | En+ | ✔️ | Apache-2.0 | | [MOSS-TTS](#moss-tts) | ✔️ | ❌ | 20 | ✔️ | Apache-2.0 | | [SoulX-Singer](#soulx-singer) | ✔️ (Singing) | ❌ | Zh/En/Canto | ✔️ | Apache-2.0 | | [SoproTTS](#soprotts) | ✔️ | ❌ | En | ✔️ | Apache-2.0 | | [NeuTTS](#neutts) | ✔️ | ❌ | En/Es/De/Fr | ✔️ | Apache-2.0 | | [Qwen3-TTS](#qwen3-tts) | ✔️ | ❌ | 10 | ✔️ | Apache-2.0 | | [GLM-TTS](#glm-tts) | ✔️ | ❌ | Zh/En | ✔️ | Apache-2.0 | | [VibeVoice-Realtime](#vibevoice-realtime) | ✔️ | ❌ | Multi | ✔️ | MIT | | [Fun-CosyVoice 3.0](#fun-cosyvoice-30) | ✔️ | ❌ | 9 + 18 dialects | ✔️ | Apache-2.0 | | [MioTTS-2.6B](#miotts-26b) | ✔️ | ❌ | En/Jp | ✔️ | LFM | | [Supertonic 2](#supertonic-2) | ❌ | ❌ | 5 | ✔️ | OpenRAIL-M | | [KugelAudio](#kugelaudio) | ✔️ | ❌ | 23 EU | ✔️ | MIT | | [Kokoro-82M](#kokoro-82m) | ✔️ | ❌ | 8 (54 voices) | ✔️ | Apache-2.0 | | [KokoClone](#kokoclone) | ✔️ | ❌ | 7 | ✔️ | Apache-2.0 | | [IndexTTS2](#indextts2) | ✔️ | ❌ | Zh/En | ✔️ | Apache-2.0 | | [Maya1](#maya1) | ✔️ | ❌ | En | ✔️ | Apache-2.0 | | [LFM2-Audio-1.5B](#lfm2-audio-15b) | ✔️ | ✔️ | En | ✔️ | LFM | | [Step-Audio-EditX](#step-audio-editx) | ✔️ | ❌ | Zh/En/Jp/Ko | ✔️ | Apache-2.0 | | [FireRedTTS2](#fireredtts2) | ✔️ | ❌ | 7 langs | ✔️ | Apache-2.0 | | [VoxCPM](#voxcpm) | ✔️ | ❌ | Zh/En | ✔️ | Apache-2.0 | | [LuxTTS](#luxtts) | ✔️ | ❌ | - | ✔️ | Apache-2.0 | | [MegaTTS3](#megatts3) | ✔️ | ❌ | Zh/En | ✔️ | Apache-2.0 | | [Spark-TTS](#spark-tts) | ✔️ | ❌ | Zh/En | ✔️ | Apache-2.0 | | [Fish Speech](#fish-speech) | ✔️ | ❌ | 8 langs | ✔️ | Apache-2.0 | | [Step-Audio](#step-audio) | ✔️ | ✔️ | Zh/En/Jp | ✔️ | Apache-2.0 | | [SoulX-Podcast](#soulx-podcast) | ✔️ | ❌ | Zh/En/Canto | ✔️ | Apache-2.0 | | [Chatterbox](#chatterbox) | ✔️ | ❌ | 23+ | ✔️ | MIT | | [Orpheus-TTS](#orpheus-tts) | ✔️ | ❌ | Multi | ✔️ | Apache-2.0 | | [Dia](#dia) | ✔️ | ❌ | En | ✔️ | Apache-2.0 | | [VieNeu-TTS](#vieneu-tts) | ✔️ | ❌ | Vi | ✔️ | Apache-2.0 | | [MiMo-Audio](#mimo-audio) | ✔️ | ✔️ | Multi | ✔️ | Apache-2.0 | | [Kimi-Audio](#kimi-audio) | ✔️ | ✔️ | Multi | ✔️ | MIT/Apache-2.0 | | [ZipVoice](#zipvoice) | ✔️ | ❌ | Zh/En | ✔️ | Apache-2.0 | <details id="longcat-audiodit"> <summary>LongCat-AudioDiT</summary> ### LongCat-AudioDiT **Description:** State-of-the-art diffusion-based TTS model operating directly in waveform latent space. Developed by Meituan's LongCat team, it requires only a Waveform VAE and Diffusion backbone, effectively mitigating compounding errors. **Release Date:** March 30, 2026 | Feature | Value | |---------|-------| | **Parameters** | 1B / 3.5B | | **Zero-shot Voice Cloning** | ✔️ | | **ASR** | ❌ | | **Pronunciation Control** | ❌ | | **Emotion Control** | ❌ | | **Languages** | Chinese, English | | **Streaming** | ❌ | | **Sample Rate** | 24000 Hz | | **License** | MIT | **Key Innovation:** Adaptive Projection Guidance (APG) replaces traditional classifier-free guidance for elevated generation quality. Outperforms Seed-TTS on zero-shot voice cloning benchmarks. **Links:** [
5
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:6e84af97c722ad9d, desc:music generation