Enables the extraction of content from Bilibili videos to be processed into structured knowledge articles and summaries.
Uses Google Gemini as a default AI provider to generate multi-layer summaries and structured knowledge articles from video transcripts.
Uses OpenAI's AI models to generate multi-layer summaries and structured knowledge articles from video transcripts.
Enables the extraction of content from YouTube videos to be processed into structured knowledge articles and summaries.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Open CLAW Knowledge Distiller Summarize https://youtube.com/watch?v=dQw4w9WgXcQ using the academic style"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Turn YouTube, Bilibili, and Facebook videos into structured knowledge articles in seconds — locally, for free. 秒速将 YouTube、Bilibili、Facebook 视频转化为结构化知识文章 — 本地运行，完全免费。
Open CLAW Knowledge Distiller（龍蝦知識蒸餾器，kd）is an open-source CLI tool and MCP server built for the Open CLAW AI agent ecosystem. It converts YouTube, Bilibili, and Facebook videos into structured knowledge articles — automatically, locally, and for free.
How it works:
If the video has subtitles → extracts them directly (no transcription needed, faster)
If no subtitles → downloads audio and transcribes locally with Qwen3-ASR MLX on Apple Silicon (no API key, no cloud cost)
Optionally generates a multi-layer AI summary: one-sentence essence + key points + cleaned transcript
Who is it for?
Researchers and students who need to digest hours of video content quickly
AI agent users (Claude Code / Open CLAW 龍蝦) who want to process videos programmatically
Anyone who wants structured notes from videos without watching them in full
Feature | Details |
🎙️ Local ASR | Qwen3-ASR MLX runs entirely on-device (Apple Silicon). No API key, no cloud, free forever. |
📝 Smart subtitle detection | Auto-detects existing subtitles — skips ASR for faster processing |
🤖 AI summarization | Supports Google Gemini, OpenAI, and Anthropic as summary providers |
🎨 8 summary styles | Standard, Academic, Action List, News Brief, Investment Analysis, Podcast Digest, ELI5, Bullet Notes |
🔌 MCP Server | Connect from Claude Code, Open CLAW, or any MCP-compatible AI agent |
🌏 Multilingual | Cantonese (粵語), Mandarin, English, Japanese, Korean, and 50+ languages |
⚡ Zero API key mode |
|
Prerequisites:
brew install ffmpeg # audio extractionInstall:
pip install openclaw-knowledge-distiller
# or with uv:
uv add openclaw-knowledge-distillerQwen3-ASR model (~1-2 GB) downloads automatically from Hugging Face on first use.
Install from source (for development):
git clone https://github.com/destinyfrancis/openclaw-knowledge-distiller.git
cd openclaw-knowledge-distiller
uv sync# ── No API key needed (100% local) ────────────────────────────────
kd process "https://youtube.com/watch?v=dQw4w9WgXcQ" --no-summary
# Cantonese video with dialect hint
kd process "https://youtube.com/watch?v=..." \
--language yue \
--asr-prompt "這是粵語口語對話，請保留懶音" \
--no-summary
# ── With AI summary ────────────────────────────────────────────────
kd config set api-key "AIzaSy..." # Google Gemini (default provider)
kd process "https://youtube.com/watch?v=..."
# Save as Markdown file
kd process "https://youtube.com/watch?v=..." --output notes.md
# ── Choose a summary style ─────────────────────────────────────────
kd process "https://youtube.com/watch?v=..." --style investment
kd process "https://youtube.com/watch?v=..." --style academic
kd process "https://youtube.com/watch?v=..." --style podcast
kd process "https://youtube.com/watch?v=..." --style eli5
# List all available styles
kd styles
# ── Other AI providers ─────────────────────────────────────────────
kd process "..." --provider openai --model gpt-4o-mini
kd process "..." --provider anthropic --model claude-haiku-4-5-20251001Run kd styles to list all styles. Choose with --style <key>:
Key | Name | Best For | |
| 📋 | Standard Summary | General videos (default) |
| 🎓 | Academic Notes | Lectures, research talks, conference papers |
| ✅ | Action List | Tutorials, how-to guides, step-by-step videos |
| 📰 | News Brief | Interviews, current events, news commentary |
| 📈 | Investment Analysis | Finance, stocks, crypto, macro economics |
| 🎙️ | Podcast Digest | Conversations, talk shows, Q&A sessions |
| 🧒 | Explain Like I'm 5 | Tech, science, academic topics for a general audience |
| ⚡ | Bullet Notes | Ultra-concise, fast scanning, quick reference |
kd process <url>Full pipeline: detect subtitles → transcribe (if needed) → summarize.
Flag | Default | Description |
| auto-detect | Language code: |
|
| Summary style preset (run |
|
| AI provider: |
| provider default | AI model name (e.g. |
| — | Custom summarization prompt (overrides |
| stdout | Output file path |
|
| Output format: |
| false | Always use ASR, skip subtitle detection |
| false | Transcript only — no AI, no API key needed |
|
| ASR backend: |
|
| Qwen3-ASR size: |
| — | Context hint for ASR (e.g. dialect, domain, speaker style) |
kd stylesList all built-in summary style presets.
kd subtitles <url>Extract subtitles only — no ASR, no AI.
kd config set <key> <value>Key | Example |
|
|
|
|
|
|
|
|
|
|
kd mcp-serverStart the MCP server on stdio transport for Claude Code / Open CLAW.
Add to ~/.claude.json:
{
"mcpServers": {
"knowledge-distiller": {
"command": "kd",
"args": ["mcp-server"],
"env": {
"KD_API_KEY": "your-api-key-here",
"KD_PROVIDER": "google"
}
}
}
}Tool | Description |
| Submit a video URL → returns |
| Poll job progress: |
| Get result: |
| List all submitted jobs |
| Update provider, model, default prompt |
Agent → process_url(url="https://youtube.com/watch?v=...", style="investment", language="zh")
← { "job_id": "a1b2c3d4" }
Agent → get_status(job_id="a1b2c3d4")
← { "status": "transcribing", "progress": 0.6, "phase": "Transcribing audio..." }
Agent → get_result(job_id="a1b2c3d4", format="summary")
← {
"one_sentence": "核心投資論點...",
"key_points": ["【投資論點】...", "【風險因素】..."]
}Config file: ~/.config/knowledge-distiller/config.toml
provider = "google"
model = "gemini-2.5-flash"
language = "zh"
transcriber = "qwen3-asr"
default_prompt = ""Environment variables (override config file):
export KD_PROVIDER=google
export KD_API_KEY=AIzaSy...
export KD_MODEL=gemini-2.5-flash
export KD_LANGUAGE=zhPython 3.11+
macOS with Apple Silicon (M1/M2/M3/M4) — required for Qwen3-ASR and mlx-whisper local inference
ffmpeg: brew install ffmpeg
qwen-asr: pip install qwen-asr
mlx-whisper: pip install mlx-whisper (alternative ASR backend)
Related MCP server: video-toolkit-mcp
Open CLAW Knowledge Distiller（龍蝦知識蒸餾器，kd）係一個專為 Open CLAW（龍蝦）AI agent 生態系統而設計的開源命令行工具同 MCP 伺服器，可以自動將 YouTube、Bilibili 同 Facebook 影片轉化為結構化知識文章。
處理流程：
若影片有字幕 → 直接提取（無需 ASR 轉錄，速度更快）
若無字幕 → 下載音頻，用 Qwen3-ASR MLX 本地轉錄（Apple Silicon，無需 API Key，零費用）
可選：用 AI 生成多層摘要（一句精華 + 要點列表 + 修正轉錄）
適合誰使用？
需要快速消化大量影片內容的研究者和學生
使用 Claude Code / Open CLAW（龍蝦）的 AI agent 用戶
想從影片獲取結構化筆記而無需完整觀看的人
功能 | 說明 |
🎙️ 本地 ASR | Qwen3-ASR MLX 完全在設備上運行（Apple Silicon），無 API 費用，永久免費 |
📝 智能字幕偵測 | 自動偵測並提取現有字幕，有字幕就跳過 ASR，速度更快 |
🤖 AI 摘要 | 支援 Google Gemini、OpenAI、Anthropic |
🎨 8 種摘要風格 | 標準、學術、行動清單、新聞速報、投資分析、播客速覽、深入淺出、極簡子彈 |
🔌 MCP 伺服器 | 可從 Claude Code、Open CLAW 或任何 MCP 相容 AI agent 連接 |
🌏 多語言 | 粵語、普通話、英語、日語、韓語及 50+ 種語言 |
⚡ 零 API Key 模式 |
|
brew install ffmpeg # 音頻提取工具
pip install openclaw-knowledge-distiller
# 或使用 uv：
uv add openclaw-knowledge-distillerQwen3-ASR 模型（約 1-2 GB）首次使用時自動從 Hugging Face 下載，無需手動操作。
從原始碼安裝（開發用）：
git clone https://github.com/destinyfrancis/openclaw-knowledge-distiller.git
cd openclaw-knowledge-distiller
uv sync# ── 無需 API Key（完全本地）──────────────────────────────────────
kd process "https://youtube.com/watch?v=..." --no-summary
# 粵語影片
kd process "https://youtube.com/watch?v=..." \
--language yue \
--asr-prompt "這是粵語口語對話，請保留懶音" \
--no-summary
# ── 使用 AI 摘要（需要 API Key）──────────────────────────────────
kd config set api-key "AIzaSy..." # 設定 Google Gemini（預設）
kd process "https://youtube.com/watch?v=..."
# 儲存為 Markdown
kd process "https://youtube.com/watch?v=..." --output notes.md
# ── 選擇摘要風格 ───────────────────────────────────────────────────
kd process "https://youtube.com/watch?v=..." --style investment # 投資分析
kd process "https://youtube.com/watch?v=..." --style academic # 學術筆記
kd process "https://youtube.com/watch?v=..." --style podcast # 播客速覽
kd process "https://youtube.com/watch?v=..." --style eli5 # 深入淺出
kd process "https://youtube.com/watch?v=..." --style bullets # 極簡子彈
# 列出所有可用風格
kd styles執行 kd styles 查看完整列表，使用 --style <key> 選擇：
Key | 名稱 | 最適合 | |
| 📋 | 標準摘要 | 一般影片（預設） |
| 🎓 | 學術筆記 | 學術演講、研究討論、學術報告 |
| ✅ | 行動清單 | 教程、How-to、步驟指引 |
| 📰 | 新聞速報 | 訪談、時事、新聞評論 |
| 📈 | 投資分析 | 財經、股票、加密貨幣、宏觀經濟 |
| 🎙️ | 播客速覽 | 對話、訪問、脫口秀 |
| 🧒 | 深入淺出 | 科技、科學、複雜主題 |
| ⚡ | 極簡子彈 | 極速瀏覽、快速筆記 |
kd process <url>旗標 | 預設值 | 說明 |
| 自動偵測 | 語言代碼： |
|
| 摘要風格（執行 |
|
| AI 供應商： |
| 供應商預設 | AI 模型名稱（例如 |
| — | 自訂摘要 prompt（覆蓋 |
| 標準輸出 | 輸出檔案路徑 |
|
| 輸出格式： |
| false | 跳過字幕偵測，強制使用 ASR |
| false | 純轉錄模式，無需 AI，無需 API Key |
|
| ASR 引擎： |
|
| Qwen3-ASR 模型大小： |
| — | ASR 上下文提示（例如方言、領域、語氣） |
在 ~/.claude.json 加入：
{
"mcpServers": {
"knowledge-distiller": {
"command": "kd",
"args": ["mcp-server"],
"env": {
"KD_API_KEY": "你的 API Key",
"KD_PROVIDER": "google"
}
}
}
}Agent → process_url(url="https://youtube.com/watch?v=...", style="investment", language="zh")
← { "job_id": "a1b2c3d4" }
Agent → get_status(job_id="a1b2c3d4")
← { "status": "transcribing", "progress": 0.6 }
Agent → get_result(job_id="a1b2c3d4", format="summary")
← {
"one_sentence": "核心投資論點...",
"key_points": ["【投資論點】...", "【風險因素】..."],
"full_transcript": "..."
}Python 3.11+
macOS Apple Silicon（M1/M2/M3/M4）— Qwen3-ASR MLX 本地推理必需
ffmpeg：brew install ffmpeg
qwen-asr：pip install qwen-asr
Open CLAW Knowledge Distiller（龙虾知识蒸馏器，kd）是一款专为 Open CLAW AI 智能体生态系统设计的开源命令行工具和 MCP 服务器。它能自动将 YouTube、Bilibili 和 Facebook 视频转化为结构化知识文章，完全本地运行，无需任何云端费用。
工作流程：
若视频有字幕 → 直接提取（最快，无需转录）
若无字幕 → 下载音频，用 Qwen3-ASR MLX 在本地转录（Apple 芯片，无需 API 密钥）
将转录文本和风格提示词返回给 Open CLAW，由智能体自行完成摘要生成
核心设计理念： kd 只负责下载和转录这两件重活，摘要生成交给龙虾自己的 AI 来完成——无需额外的 AI API 密钥。
功能 | 说明 |
🎙️ 本地 ASR | Qwen3-ASR MLX 完全在设备上运行（Apple 芯片），无 API 费用，永久免费 |
📝 智能字幕检测 | 自动检测并提取现有字幕，有字幕直接跳过 ASR，速度更快 |
🤖 智能体摘要 | 返回转录文本和提示词，由 Open CLAW 自身 AI 完成摘要，无需额外 API 密钥 |
🎨 8 种摘要风格 | 标准、学术、行动清单、新闻速报、投资分析、播客速览、深入浅出、极简子弹 |
🔌 MCP 服务器 | 可从 Claude Code、Open CLAW 或任何兼容 MCP 的 AI 智能体连接 |
🌏 多语言支持 | 粤语、普通话、英语、日语、韩语及 50+ 种语言 |
⚡ 零 API 密钥模式 |
|
brew install ffmpeg # 音频提取工具
pip install openclaw-knowledge-distiller
# 或使用 uv（推荐）：
uv add openclaw-knowledge-distillerQwen3-ASR 模型（约 1-2 GB）首次使用时自动从 Hugging Face 下载，无需手动操作。
# ── 零 API 密钥，纯本地转录 ─────────────────────────────────────
# 直接转录，输出文本
kd process "https://www.bilibili.com/video/BV..." --no-summary
# 指定普通话
kd process "https://www.bilibili.com/video/BV..." \
--language zh \
--no-summary
# 指定粤语（广东话）
kd process "https://youtube.com/watch?v=..." \
--language yue \
--asr-prompt "这是粤语口语对话，请保留原有发音特色" \
--no-summary
# ── 配置 AI 摘要（可选，需要 API 密钥）───────────────────────────
kd config set api-key "AIzaSy..." # 设置 Google Gemini（默认）
kd process "https://youtube.com/watch?v=..."
# 保存为 Markdown 文件
kd process "https://youtube.com/watch?v=..." --output 笔记.md
# ── 选择摘要风格 ───────────────────────────────────────────────────
kd process "https://youtube.com/watch?v=..." --style investment # 投资分析
kd process "https://youtube.com/watch?v=..." --style academic # 学术笔记
kd process "https://youtube.com/watch?v=..." --style actions # 行动清单
kd process "https://youtube.com/watch?v=..." --style podcast # 播客速览
kd process "https://youtube.com/watch?v=..." --style eli5 # 深入浅出
kd process "https://youtube.com/watch?v=..." --style bullets # 极简子弹
# 查看所有可用风格
kd styles使用 kd styles 查看完整列表，通过 --style <key> 选择：
Key | 名称 | 最适合 | |
| 📋 | 标准摘要 | 一般视频（默认） |
| 🎓 | 学术笔记 | 学术演讲、研究报告、学术会议 |
| ✅ | 行动清单 | 教程、操作指南、步骤说明 |
| 📰 | 新闻速报 | 采访、时事评论、新闻报道 |
| 📈 | 投资分析 | 财经、股市、加密货币、宏观经济 |
| 🎙️ | 播客速览 | 对话节目、访谈、脱口秀 |
| 🧒 | 深入浅出 | 科技、科学、复杂专业主题 |
| ⚡ | 极简子弹 | 快速浏览、会议记录、备忘 |
kd process <url>完整流程：检测字幕 → 转录（如需）→ 生成摘要。
参数 | 默认值 | 说明 |
| 自动检测 | 语言代码： |
|
| 摘要风格（运行 |
|
| AI 提供商： |
| 提供商默认 | AI 模型名称（如 |
| — | 自定义摘要提示词（覆盖 |
| 标准输出 | 输出文件路径 |
|
| 输出格式： |
| false | 跳过字幕检测，强制使用 ASR |
| false | 纯转录模式，无需 AI，无需 API 密钥 |
|
| ASR 引擎： |
|
| Qwen3-ASR 模型大小： |
| — | ASR 上下文提示（如方言特征、专业领域等） |
kd styles列出所有内置摘要风格及其提示词。
kd subtitles <url>仅提取字幕，不进行 ASR 或 AI 摘要。
kd config set <key> <value>Key | 示例 |
|
|
|
|
|
|
|
|
|
|
在 ~/.claude.json 中添加：
{
"mcpServers": {
"openclaw-knowledge-distiller": {
"command": "kd",
"args": ["mcp-server"]
}
}
}无需配置 API 密钥！ 龙虾使用自身 AI 能力完成摘要。
工具 | 说明 |
| 推荐：返回转录文本和摘要提示词，由 Open CLAW 自行完成摘要 |
| 获取所有摘要风格的完整提示词 |
| 完整流程（需配置外部 AI API 密钥） |
| 查询 process_url 任务进度 |
| 获取已完成任务的结果 |
| 列出所有任务 |
# 第一步：获取转录和提示词
龙虾 → transcribe_url(url="https://www.bilibili.com/video/BV...", style="investment", language="zh")
← {
"transcript": "今天我们来聊一下...",
"suggested_prompt": "你是一位资深投资分析师...",
"transcript_source": "qwen3-asr" // 或 "subtitles"
}
# 第二步：龙虾用自己的 AI + suggested_prompt 生成结构化摘要
# 无需任何额外 API 调用，零额外成本Python 3.11+
macOS Apple 芯片（M1/M2/M3/M4）— Qwen3-ASR MLX 本地推理必需
ffmpeg：brew install ffmpeg
Qwen3-ASR 模型会在首次使用时自动下载（约 1-2 GB）
This project stands on the shoulders of remarkable open-source work. We are deeply grateful to the following teams and individuals:
Project | Authors | Contribution |
Alibaba Qwen Team 阿里巴巴 Qwen 團隊 | The core ASR model powering local transcription. World-class multilingual speech recognition including Cantonese, Mandarin, and 50+ languages. | |
Apple Machine Learning Research | The on-device ML framework enabling Qwen3-ASR to run efficiently on Apple Silicon. | |
MLX Community Contributors | Quantized MLX model weights hosted on Hugging Face, making local inference accessible. | |
yt-dlp contributors | Robust YouTube, Bilibili, and Facebook audio download and subtitle extraction without requiring any API key. | |
Apple MLX Examples Team | Alternative Apple Silicon ASR backend using OpenAI's Whisper architecture. | |
Samuel Colvin & contributors | Data validation and modelling powering all internal data structures. | |
Sebastián Ramírez (tiangolo) | The elegant CLI framework behind the | |
Will McGugan & Textualize | Beautiful terminal output, progress bars, and formatted tables. | |
Anthropic & MCP contributors | The Model Context Protocol SDK enabling Claude Code / Open CLAW agent integration. | |
Tom Christie & encode | Async HTTP client powering AI provider API calls. |
特別感謝 阿里巴巴 Qwen 團隊開發並開源 Qwen3-ASR 模型，令本地、免費、高精度的粵語及多語言轉錄成為可能。同時感謝 yt-dlp 團隊提供強大的音頻下載同字幕提取功能，支援 YouTube、Bilibili 同 Facebook 影片。
Special thanks to the Alibaba Qwen Team for developing and open-sourcing the Qwen3-ASR model, making high-accuracy local speech recognition in Cantonese and 50+ languages possible without any cloud cost. Also grateful to the yt-dlp community for robust audio download and subtitle extraction supporting YouTube, Bilibili, and Facebook videos.
Contributions are welcome! Please open an issue or submit a pull request.
Avatar | Name | Role |
Creator & Maintainer |
MIT © 2026 destinyfrancis
This server cannot be deployed
YouTube transcripts, search, channel browsing, and playlists for AI agents via MCP.
YouTube transcripts, search, channels, playlists and bulk transcript jobs for AI agents. 14 tools.
YouTube transcripts, search, channel/playlist listings and upload tracking for AI agents.
SubDownload exposes YouTube as an MCP-native data source. Connect via OAuth and your AI agent can summarize videos, fetch full transcripts (even for videos with no captions, via AI ASR), search across channels, and save everything into a private knowledge base. Works with Claude, ChatGPT, Cursor, and 40+ MCP clients. Free credits on signup, no card required.
