pmarreck/yt-transcriber

CLI app- Give it a YouTube URL and you get a transcription with possible speaker identification and optional summary or translation, all thanks to open-source AI tooling and my lack of enough free time to watch content-sparse YouTube videos

What it solves

This tool provides a way to transcribe YouTube videos or local audio/video files into text. It eliminates the need to watch entire videos to find specific information, allowing users to read a transcript, summarize the content, or translate it into another language.

How it works

The application is a command-line interface (CLI) that uses open-source AI tooling, specifically the Whisper model for transcription. It can take a YouTube URL or a local file path as input. The tool handles the audio extraction from YouTube videos using ffmpeg and yt-dlp and then processes the audio through Whisper to generate a transcript. It also provides separate scripts for summarization and translation, which utilize OpenAI's API for these additional processing steps.

Who it’s for

Users who want to quickly process video content into text, researchers, or anyone who’s looking to save time by reading instead of watching content-sparse videos.

Highlights

  • own-source AI transcription using Whisper with multiple model sizes (base, small, medium, large, large-v2) available.
  • Support for both YouTube URLs and local audio/video files via ffmpeg.
  • Integrated caching system for transcripts and audio to avoid redundant processing.
  • Optional summarization and translation capabilities via OpenAI API integration.
  • Deterministic installation via Nix for simplified dependency management.

Related

  • Project
    wendy7756/AI-Video-Transcriber

    An AI-powered tool to transcribe, summarize, and archive videos and podcasts from 30+ platforms or local files using Faster-Whisper and LLMs.

  • Project
    Makememo/MemoAI

    An AI-powered tool for transcribing audio and video from local files or YouTube links, providing translation and subtitling capabilities.

  • Project
    Blue-B/WhisperSubTranslate

    A local application that converts video audio into multilingual subtitles using whisper.cpp for transcription and Hy-MT2 or cloud APIs for translation.

  • Project
    pluja/whishper

    An open-source, 100% local audio transcription and subtitling suite with a web UI that uses FasterWhisper for fast, private processing.

  • Project
    Anil-matcha/AI-Youtube-Shorts-Generator

    An open-source AI tool that converts long YouTube videos into viral vertical shorts by using LLMs for highlight detection and Whisper for transcription.