Talkthrough — Claude Code MCP server: video to transcript
A local MCP server that turns a screen recording or a public video link into a searchable transcript, key frames, OCR text and wall-clock timestamps.
claude mcp add --env TALKTHROUGH_WHISPER_MODEL=<TALKTHROUGH_WHISPER_MODEL> --env TALKTHROUGH_OCR=<TALKTHROUGH_OCR> --env TALKTHROUGH_OCR_LANG=<TALKTHROUGH_OCR_LANG> --env TALKTHROUGH_HOME=<TALKTHROUGH_HOME> --env TALKTHROUGH_MAX_DOWNLOAD_BYTES=<TALKTHROUGH_MAX_DOWNLOAD_BYTES> --transport stdio talkthrough -- uvx talkthrough-mcpWhat Talkthrough does
Point it at a .mov or .mp4 with narration, or at a public URL. It indexes the file into a transcript, saved frames, text read off the picture and marks tied to real playback time. Processing happens on your own machine; nothing gets uploaded.
The server ships 9 tools and 6 prompts, with speaker diarization as an option. The plugin adds slash commands such as /talkthrough:bug and /talkthrough:triage-recording, plus a triage subagent and a skill that walks the model through the flow. The agent drafts an issue but never files it; posting stays with your own gh or tracker.
You need uv. uvx resolves the Python version and the server environment for you. Expect the first process_media call to take a while: speech and OCR models are fetched then. No system ffmpeg? A bundled build is used instead. Updating the plugin can rebuild the environment and pull that build again. Register the server once only, either as a bare server or as the full plugin, not both.
What it helps with
- turn a recorded bug into a written transcript
- grab the frame where an error shows up
- read text off screen and map it to a timestamp
- draft an issue from a meeting recording
- index a public demo link without downloading it by hand
Example prompts for the agent
- Process
checkout-bug.mp4and draft an issue with frames and timestamps - Run this video through talkthrough and find where the error appears
- Transcribe the recording and pull the on-screen text
How to install Talkthrough
Platform CLI
claude mcp add --env TALKTHROUGH_WHISPER_MODEL=<TALKTHROUGH_WHISPER_MODEL> --env TALKTHROUGH_OCR=<TALKTHROUGH_OCR> --env TALKTHROUGH_OCR_LANG=<TALKTHROUGH_OCR_LANG> --env TALKTHROUGH_HOME=<TALKTHROUGH_HOME> --env TALKTHROUGH_MAX_DOWNLOAD_BYTES=<TALKTHROUGH_MAX_DOWNLOAD_BYTES> --transport stdio talkthrough -- uvx talkthrough-mcpReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from talkthrough-mcp <command>
Platform CLI
codex mcp add talkthrough --env TALKTHROUGH_WHISPER_MODEL=<TALKTHROUGH_WHISPER_MODEL> --env TALKTHROUGH_OCR=<TALKTHROUGH_OCR> --env TALKTHROUGH_OCR_LANG=<TALKTHROUGH_OCR_LANG> --env TALKTHROUGH_HOME=<TALKTHROUGH_HOME> --env TALKTHROUGH_MAX_DOWNLOAD_BYTES=<TALKTHROUGH_MAX_DOWNLOAD_BYTES> -- uvx talkthrough-mcpReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from talkthrough-mcp <command>
Config file
{
"mcpServers": {
"talkthrough": {
"command": "uvx",
"args": [
"talkthrough-mcp"
],
"env": {
"TALKTHROUGH_WHISPER_MODEL": "<TALKTHROUGH_WHISPER_MODEL>",
"TALKTHROUGH_OCR": "<TALKTHROUGH_OCR>",
"TALKTHROUGH_OCR_LANG": "<TALKTHROUGH_OCR_LANG>",
"TALKTHROUGH_HOME": "<TALKTHROUGH_HOME>",
"TALKTHROUGH_MAX_DOWNLOAD_BYTES": "<TALKTHROUGH_MAX_DOWNLOAD_BYTES>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from talkthrough-mcp <command>
Config file
{
"servers": {
"talkthrough": {
"type": "stdio",
"command": "uvx",
"args": [
"talkthrough-mcp"
],
"env": {
"TALKTHROUGH_WHISPER_MODEL": "<TALKTHROUGH_WHISPER_MODEL>",
"TALKTHROUGH_OCR": "<TALKTHROUGH_OCR>",
"TALKTHROUGH_OCR_LANG": "<TALKTHROUGH_OCR_LANG>",
"TALKTHROUGH_HOME": "<TALKTHROUGH_HOME>",
"TALKTHROUGH_MAX_DOWNLOAD_BYTES": "<TALKTHROUGH_MAX_DOWNLOAD_BYTES>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from talkthrough-mcp <command>
Platform CLI
gemini mcp add -e TALKTHROUGH_WHISPER_MODEL=<TALKTHROUGH_WHISPER_MODEL> -e TALKTHROUGH_OCR=<TALKTHROUGH_OCR> -e TALKTHROUGH_OCR_LANG=<TALKTHROUGH_OCR_LANG> -e TALKTHROUGH_HOME=<TALKTHROUGH_HOME> -e TALKTHROUGH_MAX_DOWNLOAD_BYTES=<TALKTHROUGH_MAX_DOWNLOAD_BYTES> talkthrough uvx talkthrough-mcpReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from talkthrough-mcp <command>
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 Talkthrough
How do I install Talkthrough in Claude Code?
For the server alone, run claude mcp add talkthrough-mcp -- uvx talkthrough-mcp. For the full plugin, run /plugin marketplace add korovin-aa97/talkthrough-mcp first, then /plugin install talkthrough@talkthrough.
What does Talkthrough do?
It indexes video locally into a transcript, key frames, OCR results and wall-clock marks. Your agent then searches that evidence and writes an issue draft.
Do I need ffmpeg installed?
Not necessarily. Without a system ffmpeg the server falls back to its bundled copy, which may be downloaded again if the environment is rebuilt.
