
Open-source speech recognition toolkit with diarization, for self-hosted and edge
- Open source
- 21.1K GitHub stars
- Design and media

Open-source speech recognition toolkit with diarization, for self-hosted and edge

Self-hosted Discord bot bringing OpenAI chat, images, transcription and web search

Run Gemini API calls from the shell for media generation, file analysis and transcription

Extracts text, tables, transcripts and fields from documents, images, audio and video

Lets your agent write Python code for Azure speech-to-text, batch and real-time

Transcribes short audio files to text with Azure's Speech REST API, no SDK needed
Add animated word-by-word captions to videos from Claude, Cursor or the command line
Runs locallyLocal MCP server that transcribes audio and video files with Whisper or OpenAI
Runs locallyLocal transcription, summaries and edits for video links and audio files
Runs locallyLocal Rust server turning PDFs, Office files, web pages, images and media into Markdown
Runs locallyOffline speech-to-text and SRT subtitles in 99 languages on any major GPU
Runs locallyPrivate on-device speech to text for AI assistants: transcribe files, search dictations
Runs locallyMake images, video, voice and transcripts with Vercel AI Gateway models on your own copy
Not checked yetTranscribe audio on your Mac with MacWhisper from Claude Desktop, fully local
Runs locally