</>MCP Agents Market
Plugin

AI-Video-Transcriber

by wendy77563.2kPythonUpdated 2026-08-23

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

Claude CodeClaude DesktopCodex

AI-Video-Transcriber is a Claude Code plugin that transcribes and summarizes videos and podcasts from 30+ platforms (YouTube, TikTok, Bilibili, Apple Podcasts) or local files using AI-powered speech recognition and natural language processing. It leverages a subtitle-first architecture that instantly extracts existing captions when available, falling back to Faster-Whisper transcription only when necessary. The plugin supports multi-language summaries in 11 languages, automatic translation, and works with any OpenAI-compatible API endpoint. Developers can integrate it as a Claude Code skill, MCP server tool, Codex App plugin, or standalone CLI for agent workflows.

Key Features

Multi-platform video and podcast support for YouTube, TikTok, Bilibili, SoundCloud, and 30+ services via yt-dlp
Subtitle-first extraction for instant transcripts when native captions exist, with Faster-Whisper fallback for audio-only sources
Local file upload support for audio (.mp3, .wav, .flac, .ogg, .m4a), video (.mp4, .webm, .mkv), and plain text (.txt) formats
Multi-language AI summaries in 11 languages with automatic translation when source and target languages differ
Configurable OpenAI-compatible API endpoints (OpenAI, OpenRouter, local LLMs) with browser-based credential storage
Original video download and preview with parallel processing to minimize wall-clock time
Multiple integration modes: Claude Code skill, MCP server (stdio), Codex App plugin, and headless CLI for scripting
Real-time progress streaming via Server-Sent Events with processing mode indicators (subtitle vs. Whisper path)

Use Cases

  • 01Transcribe technical conference talks or YouTube tutorials for searchable documentation and note-taking
  • 02Generate multi-language summaries of international podcasts and webinars for research or content curation
  • 03Process local audio recordings from meetings or interviews into structured transcripts and key-point summaries
  • 04Build automated content pipelines that extract insights from video feeds using the CLI or MCP tool
  • 05Archive video content with transcripts for accessibility compliance and full-text search
  • 06Create daily digest emails from creator channels by transcribing and summarizing new uploads

Related Plugins

View more

andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Plugin216.1k

claude-mem

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

Plugin95k

Understand-Anything

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

Plugin84.9k

rtk

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Plugin82.1k

AI-Video-Transcriber — FAQ

What is the AI-Video-Transcriber Claude Code plugin?+

It's an AI-powered plugin that transcribes and summarizes videos from 30+ platforms (YouTube, TikTok, podcasts) or local media files, generating transcripts and multi-language summaries. It works as a Claude Code skill, MCP server, Codex App plugin, or standalone CLI.

How do I install the Claude Code skill?+

The skill is auto-detected when you work in the cloned repository directory. To use it globally, copy the .claude/skills/video-transcribe folder to ~/.claude/skills/ and Claude Code will pick it up automatically.

Which AI clients support this plugin?+

Claude Code and Claude Desktop (via MCP server), Codex App (via plugin manifest and MCP server), and any system with Python 3.8+ for CLI use. The MCP server uses stdio protocol and requires manual registration in each client.

Do I need API keys or paid services?+

An OpenAI-compatible API key (OpenAI, OpenRouter, local LLM) is required for AI summaries, optimization, and translation. Transcription uses Faster-Whisper locally and works without an API key, but summaries will fall back to basic formatting. The plugin itself is free and open-source.

What are the prerequisites for installation?+

Python 3.8+, FFmpeg (for audio/video processing), and at least 4 GB RAM. Install via the provided install.sh script, Docker Compose, or manual pip install from requirements.txt in a virtual environment.

Does it work with local files or only online videos?+

Both. You can process URLs from 30+ platforms or upload local files (.mp3, .mp4, .wav, .webm, .mkv, .ogg, .flac, .txt) up to 200 MB per file. Plain .txt files skip transcription and go directly to the AI processing pipeline.

How do I install AI-Video-Transcriber?+

Open the source repository on GitHub and follow its README. AI-Video-Transcriber is a plugin — MCP Agents Market links you directly to the official repo.

Is AI-Video-Transcriber free?+

AI-Video-Transcriber is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches

Audio PluginsProductivity & Workflow PluginsResearch PluginsBest MCP ServersBest SkillsBest AgentsTop rated listingsClaude Code toolsBrowse all categories