MCP server for controlling Apple Music on macOS via AppleScript, enabling playlist management, playback control, and library search through natural language.
MCP server for local speech-to-text using Whisper Large V3 (MLX), enabling audio transcription with text/timestamps/SRT output and LLM-based correction, all running offline on Apple Silicon.
Enables users to generate sound effects from text descriptions using Meta's AudioGen model. Specifically designed for Apple Silicon Macs, it supports single and batch audio generation directly from natural language prompts.
Enables read-first interaction with Apple Voice Memos: search transcripts, review action candidates, mark reviewed, prepare tasks for Codex, and render digests.
An MCP server for audio/video transcription using MLX-optimized Whisper models, offering fast performance on Apple Silicon with support for multiple output formats and batch processing.
Exposes text-to-audio sound effect generation as an MCP tool, allowing clients like Claude Desktop to generate sound effects locally using a diffusion model, with support for AMD ROCm and Apple Silicon.
Text-to-speech MCP server using the Kokoro-82M model accelerated with MLX on Apple Silicon, enabling local Claude and Codex clients to speak text aloud and convert text to audio.