"App Store" matching MCP servers:

Enables agents to submit audio files to the local Meeting Transcriber macOS app, retrieve diarized transcripts, assign speaker names, and start or stop automatic meeting detection over its localhost automation API. Everything runs on-device, so no audio or transcripts leave the Mac.

MCP server providing 115 tools to control the Windy Word voice-to-text desktop app, enabling paste, hotkeys, transcription, recording, and many other operations.

An interactive digital audio workstation as an MCP server, enabling music production with a channel rack, piano roll, mixer, effects, automation, microphone recording, and offline WAV rendering.

An MCP server that lets Claude and other MCP clients read PreSonus Studio One .song files directly and drive a running Studio One through an in-app bridge device. It exposes tools for songs, tracks, takes, markers, transport, mixer channels, meters and roughly 1,000 Studio One commands.

Lets Claude or any MCP client drive the macOS Music app locally to control playback, search the library, build and edit playlists, set favorites, and pull listening statistics like top tracks, artists, albums, and genres.

Enables seamless integration with Typecast API through the Model Context Protocol, allowing clients to manage voices, convert text to speech, and play audio in a standardized way.

Enables MCP agents to retrieve Japanese voice presets and synthesize anime-style speech, including reference-conditioned voice cloning, using the CPU of the computer running the local Gradio app.

Lets AI agents search, read and export call recordings, transcripts and AI meeting notes from Digisensus Recorder, a free open-source call recorder for macOS, and start or stop recording. Runs locally on the Mac and talks to the app over a Unix socket.

Enables Cursor, Claude, and other MCP agents to interact with the HyperWhisper app for voice transcription, model management, and recording search.

Enables local AI assistants to control and explore the macOS Music app through 12 tools for playback, playlists, songs, albums, and metadata, with full privacy and no network access.

Transcribe public videos and audio (YouTube, TikTok, Instagram, Facebook, Pinterest, Google Drive) into accurate, timestamped text from Claude, ChatGPT, Cursor or any MCP client. Spanish, English and dozens of languages auto-detected. Poll-based (transcription takes minutes), same free-beta limits as the app. Docs: https://justtranscribe.ai/mcp

Enables AI agents to drive the local YuE Studio music creation desktop app, including guided wizards, song submission, job tracking, lyric input, cancellation, and style reference queries for composing and adapting songs.

AI-powered voice transcription app for macOS using WhisperKit

Enables AI agents to control a macOS digital audio workstation end to end, handling transport, tracks, mixer, plug-in parameters, audio level measurement, bouncing and cloud delivery, with every action verified by readback from the app and optional gesture and voice control of faders. It drives the DAW through OSC, Mackie Control, Accessibility and MIDI channels, so no vendor API is required.

Provides LLMs with full access to the Ken Video API for professional video processing, including adding audio, captions, and job management.

Enables users to create and edit local video projects, add video/photo/audio/text, trim and move clips, apply templates/effects, and deploy edits to the desktop app through a live web editor.

Enables AI assistants to turn music requests into traceable local DJ collections by scanning and indexing audio, planning tracklists, managing durable download jobs, and preparing hash-checked playlists, manifests, and experimental rekordbox exports for DJ app handoff.

This service provides fast and reliable transcriptions for audio/video files and voice memos. It allows LLMs to interact with the text content of audio/video file.

Enables playing and inspecting local audio files in an MCP host with an in-conversation UI showing waveform, spectrogram, and loudness metrics, while exposing playback state and metadata to the model.

A low-latency text-to-speech MCP server that uses local Kokoro GGUF inference via TTS.cpp, providing say, get_voices, and get_status tools for AI agents to synthesize speech and manage playback queues.