Skip to main content
MCP server CX Codex

talkthru — Claude Code MCP server: what it does, how to install

Feeds narrated screen recordings to coding agents by pinning speech to frames. Runs locally with whisper.cpp and requires zero API keys.

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add talkthru -- npx -y talkthru-mcp
Open on GitHub

What talkthru does

talkthru converts voiceover screen recordings into actionable agent context. You tap through your mobile or desktop UI while explaining bugs out loud. The tool segments your video into frames and attaches transcribed remarks to the exact moment you spoke them.

Processing stays entirely on your computer. Running npx talkthru doctor --fix fetches ffmpeg alongside whisper.cpp. The watcher npx talkthru watch monitors your Downloads folder and reacts only to matching video names.

Make sure to mute audio coming from the application itself. The speech model cannot distinguish system sounds from your voice, which corrupts the transcript. Forgetting to enable the mic will result in an empty review session.

What it helps with

  • feed spoken bug walkthroughs directly to coding agents
  • pin user feedback to exact UI video frames
  • extract UI component selectors via an optional hierarchy JSON file
  • diagnose interface issues without manual screenshot cropping

Example prompts for the agent

  • Inspect the feedback from my latest talkthru recording and patch the bugs
  • Check the last talkthru session and resize the checkout button
  • Review the recorded screens and speech to fix the missing error message

How to install talkthru

Platform CLI

claude mcp add talkthru -- npx -y talkthru-mcp

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about talkthru

How do I install talkthru in Claude Code?

Run claude mcp add talkthru -- npx -y talkthru-mcp in your terminal. Then pull the required binaries by executing npx talkthru doctor --fix.

What does talkthru do?

It aligns spoken thoughts with captured video frames from your screen recording. The agent receives a markdown summary with timestamps and frame paths.

Does talkthru send my video or audio to cloud APIs?

No cloud services or API tokens are involved. Everything processes locally on your machine using ffmpeg and whisper.cpp.

Similar MCP servers

All MCP servers for Agent setup: memory, context, orchestration →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor