MimikaStudio

<div align="center"> <img src="assets/light-mode-logo.png" alt="MimikaStudio Logo" width="400"/> <br><br> <code>v2026.04.1</code>&nbsp;&nbsp;macOS (Apple Silicon) · MLX Native <br><br> <h1>Clone any voice <i>in seconds</i> + Agentic Voice Cloning Server</h1> <p>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.<br>Optimized for Apple Silicon with native Metal acceleration via MLX.</p> <br> <a href="https://boltzmannentropy.github.io/mimikastudio.github.io/"><strong>Get Started</strong></a>&nbsp;&nbsp;&nbsp;·&nbsp;&nbsp;&nbsp;<a href="https://github.com/BoltzmannEntropy/MimikaStudio"><strong>View on GitHub</strong></a> <br><br> macOS (Apple Silicon) · MLX-Audio · Source Available <br><br> <b>Windows support coming soon</b> — the codebase runs on Windows, but <a href="https://boltzmannentropy.github.io/mimikastudio.github.io/">we currently provide macOS binaries only.</a> <br><br> </div>

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

Current UI Screens

| Screen | Image | |-------|-------| | AI Models | assets/screen-models-ai-models.png | | Kokoro TTS | assets/screen-kokoro-tts.png | | Supertonic TTS | assets/screen-supertonic-tts.png | | Qwen3-TTS Preset Voice | assets/screen-qwen3-preset-voice.png | | Qwen3-TTS Voice Clone | assets/screen-qwen3-voice-clone.png | | Chatterbox | assets/screen-chatterbox-voice-clone.png | | Read Aloud | assets/screen-read-aloud.png | | Audiobook Generation | assets/screen-audiobook-generation.png | | Jobs | assets/screen-jobs.png | | Voice Prompt Management | assets/screen-voice-prompt-management.png | | Settings > MCP | assets/screen-settings-mcp.png | | Settings > About | assets/screen-settings-about.png | | Settings > Pro | assets/screen-settings-pro.png |

---

Supported Models

| Model | Parameters | Type | Languages | |-------|-----------|------|-----------| | Kokoro-82M | 82M | Fast TTS | English (British RP + American) | | Qwen3-TTS 0.6B Base | 600M | Voice Cloning | 10 languages | | Qwen3-TTS 1.7B Base | 1.7B | Voice Cloning | 10 languages | | Qwen3-TTS 0.6B CustomVoice | 600M | Preset Speakers | 4 languages (en, zh, ja, ko) | | Qwen3-TTS 1.7B CustomVoice | 1.7B | Preset Speakers | 4 languages (en, zh, ja, ko) | | Qwen3-TTS 0.6B Base-8bit | 600M | Voice Cloning (8-bit) | 10 languages | | Qwen3-TTS 1.7B Base-8bit | 1.7B | Voice Cloning (8-bit) | 10 languages | | Qwen3-TTS 0.6B CustomVoice-8bit | 600M | Preset Speakers (8-bit) | 4 languages (en, zh, ja, ko) | | Qwen3-TTS 1.7B CustomVoice-8bit | 1.7B | Preset Speakers (8-bit) | 4 languages (en, zh, ja, ko) | | Chatterbox Multilingual | — | Voice Cloning | 23 languages | | Supertonic-2 | — | Multilingual TTS (ONNX) | 5 languages (en, ko, es, pt, fr) |

Audio Samples

Listen to samples generated by each TTS engine. For voice cloning demos, compare the reference voice with the generated output.

Listen to All Long Audiobooks (Inline)

The section below embeds every long-form audiobook demo so users can listen directly from the README (similar to ebook2audiobook style demo blocks).

If your GitHub client/browser does not render inline players, use the direct MP3 links under each demo.

<details> <summary><strong>Sherlock - Yelena (43m 20s)</strong></summary> <br> <audio controls preload="none" src="backend/data/pregenerated/audiobooks/long-sherlock-yelena.mp3"></audio> <br> <a href="backend/data/pregenerated/audiobooks/long-sherlock-yelena.mp3">Direct MP3 link</a> </details> <details> <summary><strong>Sherlock - Mikhail (45m 36s)</strong></summary> <br> <audio controls preload="none" src="backend/data/pregenerated/audiobooks/long-sherlock-mikhail.mp3"></audio> <br> <a href="backend/data/pregenerated/audiobooks/long-sherlock-mikhail.mp3">Direct MP3 link</a> </details> <details> <summary><strong>Sherlock - Anastasia (43m 40s)</strong></summary> <br> <audio controls preload="none" src="backend/data/pregenerated/audiobooks/long-sherlock-anastasia.mp3"></audio> <br> <a href="backend/data/pregenerated/audiobooks/long-sherlock-anastasia.mp3">Direct MP3 link</a> </details> <details> <summary><strong>Sherlock - Svetlana (43m 55s)</strong></summary> <br> <audio controls preload="none" src="backend/data/pregenerated/audiobooks/long-sherlock-svetlana.mp3"></audio> <br> <a href="backend/data/pregenerated/audiobooks/long-sherlock-svetlana.mp3">Direct MP3 link</a> </details> <details> <summary><strong>Meditations - Emma (12m 28s)</strong></summary> <br> <audio controls preload="none" src="backend/data/pregenerated/audiobooks/long-meditations-emma.mp3"></audio> <br> <a href="backend/data/pregenerated/audiobooks/long-meditations-emma.mp3">Direct MP3 link</a> </details> <details> <summary><strong>Meditations - George (13m 36s)</strong></summary> <br> <audio controls preload="none" src="backend/data/pregenerated/audiobooks/long-meditations-george.mp3"></audio> <br> <a href="backend/data/pregenerated/audiobooks/long-meditations-george.mp3">Direct MP3 link</a> </details>

Featured Qwen3 Long-Form Audiobooks

Full "A Scandal in Bohemia" audiobook chapters generated with Qwen3-TTS voice cloning. These are the primary long-form Qwen demos bundled with the repo.

| Voice | Duration | Sample | |-------|----------|--------| | Yelena | 43m 20s | long-sherlock-yelena.mp3 | | Mikhail | 45m 36s | long-sherlock-mikhail.mp3 | | Anastasia | 43m 40s | long-sherlock-anastasia.mp3 | | Svetlana | 43m 55s | long-sherlock-svetlana.mp3 |

Qwen3-TTS Voice Clone

Voice cloning from a 3-second sample. Compare the reference voice with the generated output.

| Voice | Reference | Generated | |-------|-----------|-----------| | Yelena Clone (Genesis4 Style) | Yelena.wav | qwen3-yelena-genesis4-demo.wav | | Svetlana Clone (Genesis4 Style) | Svetlana.wav | qwen3-svetlana-genesis4-demo.wav | | Yelena (Hebrew) (Cross-language) | Yelena.wav | qwen3-yelena-hebrew-demo.wav |

MimikaStudio also ships with 8 custom-designed reference voices for local cloning workflows: Alistair, Anastasia, Beatrice, Eleanor, Harriet, Mikhail, Svetlana, and Yelena.

Qwen3-TTS CustomVoice (Preset Speakers)

| Speaker | Sample | |---------|-------