Local MCP server: recordings or public video URLs into transcript, frames, OCR, wall-clock evidence.
Connect Runs on your machine
claude mcp add talkthrough-mcp -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> -- uvx talkthrough-mcp==0.4.4{
"mcpServers": {
"talkthrough-mcp": {
"command": "uvx",
"args": [
"talkthrough-mcp==0.4.4"
],
"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>"
}
}
}
}{
"mcpServers": {
"talkthrough-mcp": {
"command": "uvx",
"args": [
"talkthrough-mcp==0.4.4"
],
"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>"
}
}
}
}{
"servers": {
"talkthrough-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"talkthrough-mcp==0.4.4"
],
"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 the values in angle brackets with your own. Keys stay on your machine; we never see them.
Tools
This server runs locally, so its tools are listed by your MCP client once it starts.
Environment variables
| Name | Description |
|---|---|
TALKTHROUGH_WHISPER_MODELOptional | 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_OCROptional | Set to 'off' to disable OCR of keyframes. Default: on. |
TALKTHROUGH_OCR_LANGOptional | 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_HOMEOptional | Job store root. Default: ~/.talkthrough |
TALKTHROUGH_MAX_DOWNLOAD_BYTESOptional | Hard cap for one process_url download. Default: 2147483648 (2 GiB). |
Details
| Package | [email protected] (PYPI, stdio) |
| First published | 23 Oct 2026 |
| Last updated | 23 Oct 2026 |
| Registry name | io.github.korovin-aa97/talkthrough-mcp |
More ai and media servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.