MCP server · source category: Multimedia Process

korovin-aa97/talkthrough-mcp

Turn narrated screen recordings (or any local video/audio) into agent-ready data: local Whisper transcript, scene keyframe…

Turn narrated screen recordings (or any local video/audio) into agent-ready data: local Whisper transcript, scene keyframes, OCR, full-text search, and wall-clock anchoring that maps spoken remarks to real timestamps for log correlation. No cloud, no LLM inside. uvx talkthrough-mcp.

Open documentation ↗

Record

Type
MCP server
Category
Text, Language & Speech
Authentication
No authentication
Pricing
Free

Fields are reproduced from the source registry as-is. “Unknown” means the source did not describe the field — it is not an inference. See the methodology for how records are collected and normalised.

Browse all Text, Language & Speech MCP servers.