Podcli

Name: Podcli
Author: nmbrthirteen

@nmbrthirteen

About Podcli

Podcli is an open-source MCP server and CLI that turns long-form podcasts into upload-ready short clips for TikTok, YouTube Shorts, and Reels. It transcribes with Whisper, finds viral moments with Claude or Codex against your show's knowledge base, crops to vertical with face tra

#podcast #video #whisper #transcription #captions #ffmpeg #claude #codex #tiktok #youtube-shorts #content-creation #open-source

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "podcli": {
      "command": "node",
      "args": [
        "/path/to/podcli/dist/index.js"
      ],
      "env": {
        "PYTHON_PATH": "/path/to/podcli/venv/bin/python3"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Podcli?

Podcli is an open-source podcast clip generator that turns long-form podcasts into upload-ready TikTok, YouTube Shorts, and Reels. It runs entirely locally, requires no uploads or SaaS, and is MIT licensed. Podcli works as both a CLI tool and an MCP server, designed for use with AI agents such as Claude Code, Claude Desktop, or Codex.

How to use Podcli?

Install by cloning the repository and running ./setup.sh. Requires Node ≥18, Python ≥3.10, and FFmpeg. Use via CLI (./podcli process episode.mp4 --top 8), Web UI (npm run ui), or as an MCP server by adding the provided JSON configuration to Claude Code, Claude Desktop, or Codex. The MCP setup specifies the path to dist/index.js and the Python virtual environment.

Key features of Podcli?

Transcribes with Whisper, providing word-level timestamps and speaker diarization.
Finds viral moments using AI and a knowledge base, scoring candidates on four dimensions.
Crops to 1080×1920 with YuNet face detection and speaker-aware tracking.
Burns in captions in four styles: branded, hormozi, karaoke, subtle.
Exports with hardware encoding (VideoToolbox, NVENC, VAAPI, CPU fallback).
Provides 17 MCP tools for transcript, clips, context, and config