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 streamlines the process of downloading media from various online sources, transcribing the audio into text, and using AI to analyze or summarize the content, all within a single workflow.

How it works

VidBee integrates several tools to handle media management and AI processing:

  • Media Acquisition: It uses a shared core based on yt-dlp and FFmpeg to download video and audio from over 1,000 supported sites, including support for RSS subscriptions to automatically track and download new content from creators.
  • Local Transcription: The app runs speech recognition locally on the user's computer using models like Whisper, SenseVoice, Parakeet, and Qwen3-ASR, ensuring media doesn't need to be uploaded to external services.
  • AI Analysis: Once transcribed, the text is sent to a user-selected AI provider (such as OpenAI, Anthropic, Google, DeepSeek, or local options like Ollama and LM Studio) to perform tasks like summarization, translation, and FAQ generation.
  • Organization: It provides a detailed download queue, metadata controls for filenames and cover art, and a searchable transcript interface with timestamped playback.

Who it’s for

VidBee is ideal for researchers, students, and content creators who work with interviews, podcasts, and lectures. It allows them to quickly find specific quotes, translate recordings, and turn long recordings into structured notes.

Highlights

  • Local-First Transcription: Supports multiple local ASR models to keep data private and free from transcription service costs.
  • Cusomizable AI Prompts: Users can create and edit their own AI prompts for specific analysis tasks.
  • Automated Workflows: Includes RSS subscriptions with keyword filters and automatic tags for automated media gathering.
  • Flexible Deployment: Available as a desktop app or as a Docker-ready web API and client.
  • Comprehensive Media Control: Fine-grained control over formats (MP4, MKV, WebM), metadata embedding, and speaker identification.

Related

  • Project
    thewh1teagle/vibe

    Vibe is a cross‑platform desktop app that transcribes audio/video locally using models like Whisper, supports many languages, offers export formats, summarisation, translation, speaker diarisation, and can be driven via GUI, CLI or an HTTP API.

  • 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
    steipete/summarize

    A tool that extracts clean text from web pages, files, and audio/video media to generate LLM-powered summaries via a CLI or browser extension.

  • Project
    bugbakery/transcribee

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

  • 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.