nexmoe/VidBee

Download video and audio from YouTube , TikTok , Twitter , Instagram , Facebook , Twitch , Bilibili , and 1000+ sites—or import local media. Create searchable transcripts on your computer, then summarize, translate, or ask questions with your preferred AI provider.

What it solves

VidBee is a desktop application designed to transform video and audio files into an organized, searchable library. It eliminates the need to manually transcribe media, manually search for specific moments in recordings, or use multiple separate tools for downloading, transcribing, and summarizing content.

How it works

VidBee integrates several workflows into one app:

  1. Media Acquisition: It allows users to download media from over 1,000 sites or import local files.
  2. Local Transcription: It uses local models (such as Whisper, SenseVoice, Parakeet, and Qwen3-ASR) to generate transcripts with speaker labels and timestamps. Because this runs locally, media does not need to be uploaded to external services.
  3. AI Analysis: Users can connect various AI providers (including OpenAI, Anthropic, Google, DeepSeek, Groq, and local options like Ollama or LM Studio) to run prompts against the transcripts for tasks like summarization, translation, and FAQ generation.
  4. Organization: It includes features like RSS subscriptions for automatic downloads and flexible metadata controls for file naming and formatting.

Who it’s for

  • Researchers and Journalists: For separating speakers and finding specific quotes in interviews.
  • Podcasters: For creating searchable transcripts and organizing episodes via RSS.
  • Students and Professionals: For turning long lectures or recordings into structured notes and summaries.
  • General Users: For those who want to maintain a local, searchable archive of web video/audio content.

Highlights

  • Local-First Transcription: Supports multiple local ASR models to ensure privacy and reduce costs.
  • AI Provider Flexibility: Connects to a wide array of cloud and local LLM providers with customizable prompts.
  • ** uma RSS-driven Workflow**: Automates the acquisition of new content from creators via RSS feeds.
  • Integrated Downloader: Built-in support for 1,000+ sites using a shared yt-dlp/ffmpeg core.
  • Cross-Platform Support: Available as a desktop app and as a Docker-ready Web + API setup.

Related

  • Project
    thewh1teagle/vibe

    A private, offline audio and video transcription tool that uses AI models like Whisper to convert speech to text locally on your device.

  • 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
    pmarreck/yt-transcriber

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

  • Project
    bugbakery/transcribee

    An open-source audio and video transcription tool that generates automatic drafts using AI and supports collaborative manual editing.

  • Project
    kaixxx/noScribe

    A free, open-source application for local audio transcription and speaker identification, designed for researchers and journalists to ensure data privacy.