OmniVoice-Studio
Text to Speech
v0.5.7
VoiceStudio is a fully-local voice studio for people who want voice AI without renting it: clone a voice from a short reference recording, invent new voices …2d agoAGPL-3.0DockerModerate
Projects tagged #Transcription
~/index>
--sort
43 projects· by score
Projects
meetily
AI Assistant
v0.4.1Meetily is a privacy-first AI meeting assistant built for individuals and teams who need complete control over their meeting data.1mo agoMITNo DockerModerate
anarlog
Notes & Editors
desktop_v1.4.33anarlog is an open-source meeting notepad that keeps your work on your own machine by default.todayMITNo DockerEasy
SnapOtter
File Conversion
v2.2.0SnapOtter is an open-source file-processing suite that runs entirely on your own hardware, pitched as a private replacement for Otter.ai, TinyWow, CloudConve…3mo agoAGPL-3.0DockerDemoEasy
Vexa
Developer Tools
v0.12.28Vexa is an Apache-2.0 meeting bot and transcription API: a bot joins a Google Meet, Microsoft Teams, Zoom (Jitsi pending live validation) call and streams sp…19d agoApache-2.0DockerModerate
WhisperLive---CPU
Transcription
v0.10.0WhisperLive is a nearly-live speech-to-text server built around OpenAI's Whisper models, aimed at developers and homelab users who want low-latency transcrip…1mo agoMITDockerModerate
StemDeck
Audio Processing
v0.20.0StemDeck is a local audio tool that takes a finished track and breaks it into individual instrumental parts — a lead vocal lane, drums, bass, guitar, piano a…14d agoApache-2.0DockerEasy
Speakr
Transcription
v0.10.16-alphaSpeakr is a self-hosted web application that converts audio recordings into searchable, AI-enhanced notes for individuals and groups.3d agoAGPL-3.0DockerModerate
Speaches
Audio
v0.9.0-rc.3Speaches is a self-hosted server that implements the OpenAI Audio API for speech-to-text and text-to-speech.3mo agoMITDockerModerate
whisper-asr-webservice
Transcription
v1.10.0Whisper ASR Webservice packages three well-known speech-recognition stacks — OpenAI Whisper, Faster Whisper and WhisperX — behind one Docker HTTP service, so…2mo agoMITDockerEasy
Scriberr
Audio Processing
v1.2.0Scriberr is a self-hosted audio transcription application that processes audio and video files locally using advanced AI models including NVIDIA Parakeet, Ca…10mo agoMITDockerModerate
Whisper-WebUI
Transcription
v1.0.8Whisper-WebUI is a Gradio-based browser interface for OpenAI's Whisper, aimed at people who want subtitles without writing code.1y agoApache-2.0DockerModerate
Whishper
Audio Processing
v3.1.4Whishper is a self-hosted web application for transcribing audio and video files to text, translating transcriptions to over 60 languages, and editing subtit…1y agoAGPL-3.0DockerModerate
minutes
Notes & Editors
v0.31.1This application records conversations on your device using local speech recognition and stores them as Markdown documents with structured metadata.todayMITNo DockerModerate
Subgen generates subtitles (.srt or .lrc) for personal media libraries by transcribing audio using OpenAI Whisper models via faster-whisper and stable-ts.Subgen
Media
2mo agoMITDockerModerate
Epicenter
Notes & Editors
v7.11.0Epicenter is a monorepo of local-first applications plus the CRDT store and sync engine underneath them: each app keeps its entire dataset as one Yjs documen…11d agoNo DockerModerate
plugNmeet
Video Conferencing
v2.5.3Plug-N-Meet is a self-hosted, open-source video conferencing system built on LiveKit's WebRTC infrastructure.16d agoMITDockerDemoModerate
Opencast
Media Management
20.4A free, open-source platform for automated video capture and management built for educational institutions.5d agoECL-2.0No DockerAdvanced
FileWizard
File Conversion
0.5.1File Wizard bundles CLI tools like FFmpeg, LibreOffice, Pandoc, ImageMagick, Tesseract, and faster-whisper into a browser utility.1mo agoMITDockerModerate
edit-mind
Media Management
0.40.1Edit Mind is a local-first video knowledge base that indexes your video library with multi-modal AI analysis including transcription (Whisper), face recognit…3d agoDockerAdvanced
Rescript
Video Processing
v1.2.4Rescript is a transcript-based media editor for video and audio that runs entirely on your device — either in a Chromium-based browser or as a signed Electro…23d agoNo DockerDemoEasy
Whisper Local
Transcription
v0.23.0This desktop application provides real-time speech-to-text dictation on Windows and macOS.7d agoMITNo DockerEasy
ScribeCrate
Transcription
v2026.10.2ScribeCrate is an open-source transcription server you run on your own hardware.todayDockerDemoModerate
SayIt
Voice Assistants
v0.2.3SayIt lets Windows users dictate text by pressing a hotkey.9d agoAGPL-3.0No DockerDemoModerate
AI Native Call Center
Customer Support
v0.7.1AI Native Call Center is a self-hosted call center platform where AI voice agents answer every incoming call by default.todayApache-2.0DockerAdvanced
subarr
Media Management
v2.7.24Subarr is a coordination service that sits alongside Bazarr in the *arr media automation stack.todayMITDockerAdvanced
Prismical
Notes & Editors
v0.3.23Prismical is an open-source AI note-taking application that captures system audio from any meeting platform without a bot joining the call.24d agoMITNo DockerEasy
OpenTranscribe
Audio Processing
v0.5.1OpenTranscribe transcribes audio and video files using WhisperX and identifies speakers with PyAnnote v4.11d agoAGPL-3.0DockerModerate
