— · MIT License
Enables local voice cloning and multi-take text-to-speech synthesis on Apple Silicon, plus audio/video transcription and subtitle generation, through Claude and other MCP clients.
— · MIT License
Enables MCP clients to curate YouTube watch history and locally search selected transcripts using SQLite FTS5, ChromaDB embeddings, and reciprocal rank fusion, with tools to browse unindexed history and add videos.
— · MIT License
Renders validated declarative scene specifications into MP4 videos inside disposable, network-disabled containers, then serves an embedded player with playback controls and diagnostics through MCP Apps. Users can iteratively revise scenes conversationally, with revision history preserved and identical renders reused per account.
— · MIT License
Runs entirely local media tooling as an MCP plugin: it edits and inspects video, denoises/transcribes/normalizes audio, generates images, performs OCR, does offline text-to-speech, drives the user's logged-in Chrome via CDP, and reads or creates Office and PDF documents. Everything executes on the machine through ffmpeg, faster-whisper, MossFormer2, ComfyUI/FLUX, Tesseract, SAPI and Playwright, with no API costs or file uploads.
— · MIT License
Enables local macOS clients to retrieve video metadata, timestamped transcripts, and still frames from Loom share links or IDs through three read-only stdio tools.
— · MIT License
Enables converting natural-language mathematical descriptions into rendered Manim animation videos, returning playable MP4 links and reusable code without requiring local Manim, LaTeX, or ffmpeg installations.
— · MIT License
Connects AI agents to a creative platform's canvas, image, video, audio, subject, and storyboard capabilities, enabling natural-language parameter lookup, job submission and tracking, credit-controlled execution, and asset retrieval.