Summarize any online video or podcast in seconds. BibiGPT extracts transcripts, generates AI summaries,
and creates chapter-by-chapter breakdowns from YouTube, Bilibili, TikTok, Twitter/X, Xiaohongshu,
Apple Podcasts, and 20+ platforms. Supports async processing for long videos (2h+), custom prompts,
multiple AI models, and output in 5 languages (EN/ZH/JA/KO/ZH-TW). Trusted by 500K+ users worldwide.
Overview
BibiGPT is an AI-powered video and audio assistant that turns hours of content into actionable knowledge in seconds.
What it does:
- Summarize videos and podcasts from YouTube, Bilibili, TikTok, Twitter/X, Xiaohongshu, Douyin, Apple Podcasts, Spotify, and 20+ platforms
- Extract full transcripts with timestamps — even for videos without subtitles (powered by Whisper ASR)
- Generate chapter-by-chapter summaries for lectures, tutorials, and long-form content
- Async task processing for videos over 2 hours
Why agents love it:
- 6 MCP tools with clear, composable APIs — summarize, get subtitles, chapter breakdown, async task creation & polling
- Works with any AI model (GPT-4o, Claude, Gemini, etc.) via custom prompt config
- Output in 5 languages: English, Chinese, Japanese, Korean, Traditional Chinese
- OAuth 2.1 + Bearer token auth — compatible with Claude, ChatGPT, Cursor, Codex, and all MCP clients
Who uses it: 500,000+ users — content creators, researchers, students, and knowledge workers who process video content at scale.
Built by BibiGPT (bibigpt.co).
Server Config
{
"mcpServers": {
"bibigpt": {
"type": "http",
"url": "https://bibigpt.co/api/mcp"
}
}
}