AI-powered transcription for audio & video with Whisper — self-hosted, fast, and open-source.
whispr is a transcription pipeline built around OpenAI's Whisper model. It supports four backends (three interchangeable general-purpose ones plus an optional Mega-ASR specialist for degraded audio), parallel chunk processing, automatic fallback, and multiple output formats.
🎙️🎬 Python CLI utility to automate local video-to-subtitle workflows. Extract audio via FFmpeg and generate perfectly synced SRT/CC transcripts using OpenAI's Whisper AI models. Built for speed, accuracy and local-first privacy.
Fast, accurate, and interactive YouTube video transcript extraction tool built with React 19, TypeScript, Supabase, and Apify.
Desktop app to transcribe YouTube videos using yt-dlp, ffmpeg, and Groq Whisper. No server, no terminal.
🤖 Bot de Telegram + CLI para transcribir y resumir videos de YouTube usando NoteGPT.io, youtube-transcript-api y Gemini 3.1 Flash-Lite. Multiplataforma (TUI/GUI/daemon).
Add a description, image, and links to the youtube-transcriber topic page so that developers can more easily learn about it.
To associate your repository with the youtube-transcriber topic, visit your repo's landing page and select "manage topics."