Talkthrough MCP Server

by korovin-aa97io.github.korovin-aa97/talkthrough-mcpv0.4.2

Turn screen recordings or other local video and audio into local Whisper transcripts, keyframes, OCR and full-text search, with wall-clock timestamps for logs.

31Pythonstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Active12d ago

Install Talkthrough MCP server

claude mcp add talkthrough -- uvx talkthrough-mcp

{
  "mcpServers": {
    "talkthrough": {
      "command": "uvx",
      "args": [
        "talkthrough-mcp"
      ]
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).

{
  "mcpServers": {
    "talkthrough": {
      "command": "uvx",
      "args": [
        "talkthrough-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config (claude_desktop_config.json), then restart.

{
  "servers": {
    "talkthrough": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "talkthrough-mcp"
      ]
    }
  }
}

Add to .vscode/mcp.json in your workspace.

{
  "mcpServers": {
    "talkthrough": {
      "command": "uvx",
      "args": [
        "talkthrough-mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json.

Configuration

Variable	Required	Secret	Description
TALKTHROUGH_WHISPER_MODEL	—	—	Whisper model (tiny\|base\|small\|medium\|large-v3\|large-v3-turbo). Default: small. Use large-v3-turbo for non-English narration; the process_media `model` param overrides per call.
TALKTHROUGH_OCR	—	—	Set to 'off' to disable OCR of keyframes. Default: on.
TALKTHROUGH_OCR_LANG	—	—	Recognition script for on-screen text: a language code (ru, ja, ko, ar, hi, ...) or a RapidOCR pack name (eslav, cyrillic, ...). Default: Latin+Chinese.
TALKTHROUGH_HOME	—	—	Job store root. Default: ~/.talkthrough
TALKTHROUGH_MAX_DOWNLOAD_BYTES	—	—	Hard cap for one process_url download. Default: 2147483648 (2 GiB).