wendy7756/AI-Video-Transcriber

Transcribe and summarize videos and podcasts using AI. Open-source, multi-platform, and supports multiple languages.

What it solves

AI Video Transcriber provides a streamlined way to convert video and audio content from the web or local files into structured text. It solves the problem of manually transcribing media, summarizing long videos, and archiving source material alongside its transcript.

How it works

The tool uses a multi-path processing pipeline:

  1. Input Handling: It accepts URLs from 30+ platforms (via yt-dlp) or local file uploads (normalized via FFmpeg).
  2. Transcription: It first attempts to extract native subtitles for speed. If unavailable, it uses Faster-Whisper for high-accuracy speech-to-text.
  3. AI Enhancement: The resulting text is sent to an OpenAI-compatible LLM to correct typos, complete sentences, and organize the content into paragraphs.
  4. Post-Processing: The system can automatically translate the transcript and generate summaries in 11 different languages based on user preference.
  5. Archiving: It can optionally download the original video (up to 720p) in parallel with the transcription process for easy preview and saving.

Who it’s for

Content creators, researchers, and students who need to quickly extract insights from videos and podcasts without watching the entire media file.

Highlights

  • Subtitle-First Architecture: Dramatically increases speed by prioritizing native subtitles over AI transcription.
  • Bring Your Own Model: Supports any OpenAI-compatible API endpoint, allowing users to use local LLMs or various providers.
  • Broad Platform Support: Works with YouTube, TikTok, Bilibili, Apple Podcasts, SoundCloud, and more.
  • Agent-Ready: Includes a headless CLI, an MCP server for Claude/Codex, and dedicated skills for AI agents.
  • Local File Support: Handles a wide variety of audio/video formats and plain text files.

Related

  • Project
    pmarreck/yt-transcriber

    A CLI tool that transcribes YouTube videos or local media files using Whisper, with optional AI-powered summarization and translation.

  • Project
    Makememo/MemoAI

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

  • 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
    zh-plus/openlrc

    A Python library that transcribes audio using faster-whisper and uses LLMs to translate and polish the text into synchronized .lrc subtitles.

  • Project
    WEIFENG2333/VideoCaptioner

    An all-in-one video subtitle tool that uses LLMs for speech recognition, subtitle optimization, and translation to automate the video captioning process.