GitHub Repository

Open-source AI podcast clipper. Generate vertical clips with face tracking and burned-in captions. CLI, MCP server, web app.

9 starsPython

Open-source MCP server for AI podcast clipping

Name: Open-source MCP server for AI podcast clipping
Availability: InStock
Author: nsiradze

by nsiradze·Mar 1, 2026·1 point·0 comments

Visit Project View on HN

AI Analysis

●●SolidShip ItSolve My Problem

Audio energy + transcript heuristics suggest clips; hardware acceleration handles rendering.

Strengths

•Full pipeline from transcript to export: Whisper transcription, caption styles, smart cropping, and preset management.
•Hardware-accelerated encoding (VideoToolbox, NVENC, VAAPI) avoids CPU bottleneck on batch export.
•Web UI + CLI + MCP server cover three user workflows; knowledge base context helps tailor suggestions.

Weaknesses

•Early product with admitted missing features; no benchmarks vs competing tools (Descript, Riverside).
•Transcript quality entirely dependent on Whisper; no mention of correction or manual override workflow.

Post Description

Hello,

I just build this new tool to analyze transcripts and make podcast clipping effortless for socials like TikTok, Instagram Reels and Youtube Shorts.

This is open and free to use, i would love to get suggestions of how to make it better since it's my first open community project and also first iteration to this product which still lacks some important features

Thanks!