- whisper by openai, 113k stars. Speech recognition model trained on large-scale weakly supervised audio
- VoiceStudio by debpalash, 111k stars. Local voice cloning, dubbing, dictation and transcription app
- 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
- whisper.cpp by ggml-org, 55k stars. C and C++ port of OpenAI's Whisper speech recognition model
- Handy by cjpais, 39k stars. Offline speech-to-text desktop app built with Tauri v2
- meetily by Zackriya-Solutions, 33k stars. Meeting note taker that transcribes on-device with Whisper, no bot joins the call
- Speech by NVIDIA-NeMo, 19k stars. Framework for speech recognition, text-to-speech, and translation models
- omi by BasedHardware, 14k stars. AI wearable and companion app that uses screen and conversation context
- 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
- openwhispr by OpenWhispr, 12k stars. Voice dictation app using local Whisper or Parakeet, or cloud models
- moonshine by moonshine-ai, 12k stars. Low-latency speech to text and text to speech models for building voice agents
- WhisperLiveKit by QuentinFuxa, 11k stars. Local streaming speech-to-text with speaker diarization and translation
- anarlog by fastrepl, 9.9k stars. Local-first desktop app for AI meeting notes and transcription
- hex by anomalyco, 6.7k stars. Local voice dictation app for macOS, Windows and Linux
- OGAM by off-grid-ai, 3.4k stars. Offline app for running GGUF models, vision, speech, and image generation locally
- vexa by Vexa-ai, 3.0k stars. Open source meeting transcription API with bots for Meet, Teams and Zoom
- claude-real-video by HUANGCHIHHUNGLeo, 2.3k stars. Extracts scene-aware frames and a transcript so an LLM can review a video
- transcribe.cpp by handy-computer, 2.2k stars. C++ speech to text inference on ggml with many ASR model families
- LiveStream-Agent-Studio by HanyuanWang, 2.0k stars. Windows local agent studio for Douyin livestream analysis and clip planning
- Portable-Local-Studio by techjarves, 2.0k stars. Portable offline GUI for image generation, GGUF LLMs and speech tools
- baocut by JimLiu, 1.8k stars. AI video editor with a timeline for transcribing, subtitling and dubbing
- yogurt by FrigadeHQ, 1.5k stars. Private AI meeting notes app that runs models locally
- rescript by wassgha, 1.1k stars. Browser-based video and audio editor that edits by transcript
- CrispASR by CrispStrobe, 812 stars. C++ ggml runtime for speech recognition and TTS models with forced alignment
- macparakeet by moona3k, 788 stars. Local dictation and transcription app for Apple Silicon Macs, with a CLI
- watch-skill by oxbshw, 582 stars. Turns video, audio and screen activity into timestamped, searchable evidence for agents
- jot-gemini-transcribe-macOS by google-gemini, 557 stars. macOS hold-to-talk dictation demo that types transcribed speech
- betterwispr by opennookorg, 537 stars. Offline macOS dictation: hold a key, speak, and text is typed into any app
- yap by FrigadeHQ, 478 stars. Menu bar dictation app that transcribes speech on the Mac without an account
- omarchy-meeting-recorder by jankeesvw, 476 stars. Records mic and system audio on Omarchy, transcribed on your own machine
- yapsnap by kouhxp, 436 stars. Command line tool that transcribes video URLs or audio files on CPU
- speech-studio by timoncool, 285 stars. Offline Windows voice studio for text-to-speech, voice cloning and transcription
- open-wispr by human37, 225 stars. On-device voice dictation app for Apple Silicon Macs
- qwen-scribe by VladUZH, 224 stars. Local speech transcription and system-wide dictation for Apple Silicon Macs
- EnviousWispr by saurabhav88, 221 stars. On-device dictation for macOS using Whisper or Parakeet on Apple Silicon
- speakmore by zephyr4123, 207 stars. Voice typing and inline translation app for Mac and Windows, can run fully offline
- wispr-flow-linux by wispr-flow-linux, 205 stars. Unofficial port of a voice dictation app to Linux
- gpt-voice by entropyconquers, 109 stars. Mac dictation app that types speech into any text field using ChatGPT sign-in
New repos every two days, stars refreshed daily. Visits are counted without cookies, and the numbers are public. How it works Data RSS Newsletter