Install in seconds

Install this skill

Copy the command and run it in your terminal. You can review the source before installing.

terminal

git clone https://github.com/korovin-aa97/talkthrough-mcp

Works with Git. The repository opens in your current directory.

🎞️

DataPython

Talkthrough

by korovin-aa97

Analyzes narrated screen recordings and audio files, providing timestamped transcripts, scene keyframes, OCR text, and wall-clock anchoring via a local MCP server. Use it to triage feedback, extract meeting actions, or correlate recordings with logs.

12 stars0 forksAdded 2026/07/16

View source on GitHub Download ZIP

agent-skillsai-agentsclaudedeveloper-toolsfeedbackffmpeglocal-firstmcpmcp-servermodel-context-protocolocrpythonscreen-recordingspeech-to-texttranscriptionvideo-analysiswhisper

Documentation

README

From the original repository

talkthrough for OpenClaw

This skill wires the talkthrough MCP server into OpenClaw and teaches the workflow. Everything runs locally: recordings never leave the machine.

Setup (once)

Add the MCP server:

openclaw mcp add talkthrough --command uvx --arg talkthrough-mcp[diarization]

Requires uv (https://astral.sh/uv). First processing downloads a whisper model once (~460 MB for the default small).

Workflow

process_media(path) — idempotent by content hash; returns a compact summary with job_id (re-calls on the same file are instant).
get_transcript(job_id) / search(job_id, "<word>") — orient; search covers speech AND on-screen OCR text.
get_moment(job_id, t0-2000, t1+2000) — evidence bundle per remark: transcript slice + up to 3 frames + OCR + wall-clock range.
extract_frame(job_id, at_ms, crop=...) — exact instant, native resolution, when keyframes miss the moment.
list_jobs() — recordings processed earlier remain queryable.

Timestamps: t_ms is video-relative; t_wall is real wall-clock time when the recording start is known — use it to correlate remarks with logs (±30 s window). Audio-only files (.m4a/.mp3/…) have transcripts but no frames; frame tools erroring on them is expected.

Full docs: https://github.com/korovin-aa97/talkthrough-mcp