Happy slice of mcp pizzaMCP.pizza
MimikaStudio

MimikaStudio

MCP.Pizza Chef: BoltzmannEntropy

This is a Mac app (Apple Silicon only) that reads your documents aloud, generates speech from text, clones a voice from a short recording, and builds full audiobooks from PDFs, ebooks, or Word files. Everything runs on your own computer, so there's no account or API key needed for the core features. It also has a built-in dashboard for tracking narration jobs, and it can connect to AI assistants through MCP so they can send it text-to-speech or voice-cloning requests directly.

Files/PDF
Other

Use This MCP client To

Clone a voice from a short audio sample Turn written text into natural-sounding speech Have a PDF or ebook read aloud to me Convert a full book into a listenable audiobook Reuse a saved voice for future recordings Let an AI assistant queue up voice-cloning or narration jobs Follow along with synchronized text highlighting while listening

README

MimikaStudio Logo

v2026.04.1  macOS (Apple Silicon) · MLX Native

Clone any voice in seconds + Agentic Voice Cloning Server

Local-first voice cloning, text-to-speech, Read Aloud document reader, audiobook creator, and an agentic voice cloning server with state-of-the-art job queue orchestration.
Optimized for Apple Silicon with native Metal acceleration via MLX.


Get Started   ·   View on GitHub

macOS (Apple Silicon) · MLX-Audio · Source Available

Windows support coming soon — the codebase runs on Windows, but we currently provide macOS binaries only.

Custom Voice Cloning | Text-to-Speech | PDF Read Aloud | Audiobook Creator | MCP & API Dashboard

A local-first application for macOS (Apple Silicon) with four integrated capabilities and production-oriented workflows: clone any voice from as little as 3 seconds of reference audio using multiple engines (Qwen3-TTS and Chatterbox), generate high-quality text-to-speech with fast and expressive model families (Kokoro and Supertonic), read documents aloud with sentence-level highlighting and synchronized progression (PDF, DOCX, EPUB, Markdown, TXT), and convert full documents to audiobooks with queueable chapter generation and reusable voice presets. MimikaStudio also operates as an agentic voice cloning server with a state-of-the-art jobs queue for TTS, cloning, and audiobook pipelines. It runs fully on-device, includes first-run model download management, and exposes both UI and API paths for advanced local automation.

Featured Qwen Long-Form Audiobooks: Yelena · Mikhail · Anastasia · Svetlana

License: Source code is licensed under Business Source License 1.1 (BSL-1.1), and binary distributions are licensed under the MimikaStudio Binary Distribution License. See LICENSE, BINARY-LICENSE.txt, and the website License page.

LICENSE · BINARY-LICENSE.txt · Website License page

The codebase is cross-platform, but we currently provide macOS binaries only.

we currently provide macOS binaries only.

Note: Windows support is planned for a future release.

Latest Release

v2026.04.1 adds in-app PDF page preview for audiobook source documents, disables the old 7-day expiration and Polar/LemonSqueezy purchase flow in the Pro UI, and removes pricing/buying paths from the website in favor of direct GitHub release downloads.

Stars

MimikaStudio FAQ

Do I need to be on a Mac to use this?
Yes — MimikaStudio currently only ships as a macOS app built for Apple Silicon (M1/M2/M3/M4 chips); Windows support is planned but not yet available.
Can I use this to have my PDFs read aloud?
Yes — you can open a PDF, DOCX, EPUB, Markdown, or text file and have it read aloud with sentence-by-sentence highlighting so you can follow along.
Can I use this to turn a book into an audiobook?
Yes — you can feed in a full document and it will generate a complete audiobook, chapter by chapter, in a voice you pick or clone.
Do I need an API key or account to use it?
No API key is required for the core app — it runs entirely on your own Mac, though some purchase/licensing options exist for the Pro tier.
Does this connect to Claude, ChatGPT, or other AI assistants?
It includes an MCP server so AI assistants that support MCP (such as Claude) can send it text and voice-cloning jobs, alongside its own built-in app interface.
Is this free to use?
The source code is source-available under a business license, and the app is distributed as a free download; a Pro tier exists but the old expiring trial and purchase flow have been removed in favor of direct downloads.
How much technical setup does this take?
You download a macOS app binary and run it like any other app — no coding is required to use the core features, though the underlying project is source-available for developers.
Can it clone my own voice or someone else's?
Yes — with as little as 3 seconds of a reference recording, it can clone a voice and use it to generate new speech.