Merge pull request #9852 from korovin-aa97/add-talkthrough-mcp

Add talkthrough-mcp (Multimedia Process) 🤖🤖🤖

README.md

@@ -2579,6 +2579,7 @@ Provides the ability to handle multimedia, such as audio and video editing, play
 - [realcrabcut/crabcut-mcp-server](https://github.com/realcrabcut/crabcut-mcp-server) [![realcrabcut/crabcut-mcp-server MCP server](https://glama.ai/mcp/servers/realcrabcut/crabcut-mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/realcrabcut/crabcut-mcp-server) 📇 ☁️ - Turn YouTube videos into short-form clips from any AI assistant. AI-powered highlight detection, subtitle generation, 9:16 reframing, and direct download URLs via the Crabcut API.
 - [runapi-ai/mcp](https://github.com/runapi-ai/mcp) [![runapi-ai/mcp MCP server](https://glama.ai/mcp/servers/runapi-ai/mcp/badges/score.svg)](https://glama.ai/mcp/servers/runapi-ai/mcp) 📇 ☁️ - Unified AI model API for 130+ models across 18 providers. Browse models, check pricing, create image/video/music/audio tasks, poll results, check balance, and call LLM endpoints. Free catalog tools work without an API key. `npx @runapi.ai/mcp`
 - [keiver/image-tiler-mcp-server](https://github.com/keiver/image-tiler-mcp-server) [![image-tiler-mcp-server MCP server](https://glama.ai/mcp/servers/keiver/image-tiler-mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/keiver/image-tiler-mcp-server) 📇 🏠 🍎 🪟 🐧 - Full-resolution vision for LLMs. Tiles large images and captures web pages via Chrome CDP so vision models process every detail without downscaling. Generates interactive HTML tile previews. Supports Claude, OpenAI, Gemini presets with per-model token math and entropy-based tile classification.
+- [korovin-aa97/talkthrough-mcp](https://github.com/korovin-aa97/talkthrough-mcp) [![korovin-aa97/talkthrough-mcp MCP server](https://glama.ai/mcp/servers/korovin-aa97/talkthrough-mcp/badges/score.svg)](https://glama.ai/mcp/servers/korovin-aa97/talkthrough-mcp) 🐍 🏠 🍎 🪟 🐧 - 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`.
 - [legolev/mediamcp](https://github.com/legolev/mediamcp) [![legolev/mediamcp MCP server](https://glama.ai/mcp/servers/legolev/mediamcp/badges/score.svg)](https://glama.ai/mcp/servers/legolev/mediamcp) 📇 ☁️ 🍎 🪟 🐧 - Image generation and editing plus video generation (Veo, Sora, Seedance) via OpenRouter or any OpenAI-compatible API. Saves files to disk with token-cheap inline previews, resumable video jobs, live model listing, and a config-diagnostics tool. `npx -y mediamcp`.
 - [Lulu-The-Narwhal/dali-mcp](https://github.com/Lulu-The-Narwhal/dali-mcp) [![Lulu-The-Narwhal/dali-mcp MCP server](https://glama.ai/mcp/servers/Lulu-The-Narwhal/dali-mcp/badges/score.svg)](https://glama.ai/mcp/servers/Lulu-The-Narwhal/dali-mcp) 🐍 ☁️ - Scores AI image/video generation prompts (0-100) against 18 models (Veo 3, Sora, Kling, Runway, Seedance, Midjourney, Flux, and more) before you spend a generation credit, then rewrites weak ones. Free, hosted remote MCP + npm/PyPI packages.
 - [gaudiolab-jp/gaudio-developers-mcp](https://github.com/gaudiolab-jp/gaudio-developers-mcp) [![gaudio-developers-mcp MCP server](https://glama.ai/mcp/servers/gaudiolab-jp/gaudio-developers-mcp/badges/score.svg)](https://glama.ai/mcp/servers/gaudiolab-jp/gaudio-developers-mcp) 📇 ☁️ 🍎 🪟 🐧 - Audio AI API for stem separation (vocal, drum, bass, guitar, piano), DME separation (dialogue, music, effects), and AI lyrics sync. 7 tools, 11 models, supports WAV/FLAC/MP3/M4A/MOV/MP4.