- VoiceStudio by debpalash, 111k stars. Local voice cloning, dubbing, dictation and transcription app
- unsloth by unslothai, 80k stars. Local UI for running and fine-tuning LLMs and diffusion models
- GPT-SoVITS by RVC-Boss, 65k stars. Few-shot text-to-speech and voice cloning from about a minute of audio
- voicebox by jamiepine, 61k stars. Voice studio for cloning voices, dictation and generating speech
- VibeVoice by microsoft, 57k stars. Open-source voice AI models for speech synthesis and transcription
- airi by moeru-ai, 51k stars. Self-hosted AI companion with voice chat, VRM and Live2D avatars
- TTS by coqui-ai, 46k stars. Deep learning toolkit for text-to-speech models in research and production
- VoxCPM by OpenBMB, 42k stars. Tokenizer-free text-to-speech model with voice design and cloning
- OpenVoice by myshell-ai, 38k stars. Python model that clones a voice from a short sample and speaks new text
- Pixelle-Video by ATH-MaaS, 30k stars. Automated short video generator using LLM scripts, TTS and ComfyUI images
- readest by readest, 26k stars. Cross-platform ebook reader for EPUB files with a modern interface
- ebook2audiobook by DrewThomasson, 21k stars. Converts e-books to audiobooks with many text-to-speech engines and voice cloning
- dia by nari-labs, 19k stars. Text-to-speech model that produces multi-speaker dialogue in a single pass
- Speech by NVIDIA-NeMo, 19k stars. Framework for speech recognition, text-to-speech, and translation models
- KittenTTS by KittenML, 17k stars. Small text-to-speech model that runs on a CPU
- OmniVoice by k2-fsa, 17k stars. Voice cloning text-to-speech model covering over 600 languages
- Open-LLM-VTuber by Open-LLM-VTuber, 15k stars. Hands-free voice chat with any LLM and a local Live2D avatar
- OpenCreator by krillinai, 14k stars. Video translation, dubbing and media generation workspace powered by Codex
- speech-to-speech by huggingface, 14k stars. Pipeline for building speech-to-speech voice agents from open models
- voice-pro by abus-aikorea, 13k stars. Gradio UI for text-to-speech, voice cloning, transcription and vocal removal
- moonshine by moonshine-ai, 12k stars. Low-latency speech to text and text to speech models for building voice agents
- ten-framework by TEN-framework, 11k stars. Framework for building real-time multimodal conversational voice agents
- voltagent by VoltAgent, 11k stars. TypeScript framework and platform for building AI agents
- audiblez by santinic, 8.9k stars. Converts EPUB e-books into audiobooks using Kokoro text-to-speech
- Vision-Agents by GetStream, 8.2k stars. Framework for building low-latency voice and vision AI agents
- notebooks by unslothai, 5.8k stars. Colab and Jupyter notebooks for fine-tuning text, vision, audio and TTS models
- MOSS-TTS by OpenMOSS, 4.3k stars. Open speech models for long-form TTS, voice cloning and sound effects
- anything2explainer by Vincentwei1021, 3.3k stars. Claude Code and Codex skill that builds narrated explainer videos from a topic
- qwen-audio-agent by QwenAudio, 3.2k stars. Realtime voice runtime that lets AI agents talk and take actions
- Audio8_TTS by Edge0-AI, 2.5k stars. Small text-to-speech model designed to run at a compact size
- yovoice by leemysw, 2.2k stars. Offline audio studio for text-to-speech, voice cloning and songs
- Portable-Local-Studio by techjarves, 2.0k stars. Portable offline GUI for image generation, GGUF LLMs and speech tools
- breeze-tts by breezeblue-ai, 1.7k stars. PyTorch inference code for the Breeze 2 text-to-speech model
- airunner by Capsize-Games, 1.3k stars. Offline engine for image generation, voice chat and local LLM workflows
- AVA-AI-Voice-Agent-for-Asterisk by hkjarral, 1.3k stars. Open source AI voice agent that connects to Asterisk and FreePBX
- CrispASR by CrispStrobe, 812 stars. C++ ggml runtime for speech recognition and TTS models with forced alignment
- tiny-tts by tronghieuit, 640 stars. Small English text-to-speech model with about one million parameters
- showtime by FavioVazquez, 333 stars. Local video renderer driven by a coding agent, using ffmpeg and motion graphics
- speech-studio by timoncool, 285 stars. Offline Windows voice studio for text-to-speech, voice cloning and transcription
- NeMo-Speech.cpp by NVIDIA, 257 stars. C++ inference runtime for speech recognition and text to speech models
New repos every two days, stars refreshed daily. Visits are counted without cookies, and the numbers are public. How it works Data RSS Newsletter