Talkthrough

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.korovin-aa97/talkthrough-mcp",
  "description": "Local MCP server: recordings or public video URLs into transcript, frames, OCR, wall-clock evidence.",
  "title": "Talkthrough",
  "repository": {
    "url": "https://github.com/korovin-aa97/talkthrough-mcp",
    "source": "github"
  },
  "version": "0.4.2",
  "websiteUrl": "https://github.com/korovin-aa97/talkthrough-mcp",
  "packages": [
    {
      "registryType": "pypi",
      "registryBaseUrl": "https://pypi.org",
      "identifier": "talkthrough-mcp",
      "version": "0.4.2",
      "runtimeHint": "uvx",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "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.",
          "name": "TALKTHROUGH_WHISPER_MODEL"
        },
        {
          "description": "Set to 'off' to disable OCR of keyframes. Default: on.",
          "name": "TALKTHROUGH_OCR"
        },
        {
          "description": "Recognition script for on-screen text: a language code (ru, ja, ko, ar, hi, ...) or a RapidOCR pack name (eslav, cyrillic, ...). Default: Latin+Chinese.",
          "name": "TALKTHROUGH_OCR_LANG"
        },
        {
          "description": "Job store root. Default: ~/.talkthrough",
          "name": "TALKTHROUGH_HOME"
        },
        {
          "description": "Hard cap for one process_url download. Default: 2147483648 (2 GiB).",
          "name": "TALKTHROUGH_MAX_DOWNLOAD_BYTES"
        }
      ]
    }
  ]
}