BoltzmannEntropy/MimikaStudio
MimikaStudio - A local-first application for macOS (Apple Silicon) + Agentic MCP Support
Supports multiple state-of-the-art TTS engines (Kokoro, Qwen3-TTS, Supertonic, Chatterbox) with voice cloning from 3-second samples, document reading with synchronized highlighting across PDF/DOCX/EPUB formats, and batch audiobook generation with queueable job orchestration. Runs entirely on-device with MLX-native Metal acceleration for Apple Silicon, exposing both native UI and REST API for local automation and MCP agent integration. Built with modular model architecture supporting 8-bit quantization and multilingual synthesis across 23 languages.
357 stars.
Stars
357
Forks
52
Language
Dart
License
GPL-3.0
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/BoltzmannEntropy/MimikaStudio"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
aahl/qwen-asr2api
🎤 Qwen 3 ASR to OpenAI API, 免费STT语音识别模型
zhao-kun/VibeVoiceFusion
VibeVoiceFusion is a full-stack, multi-speaker voice generation web system featuring LoRA...
gabriele-mastrapasqua/qwen3-tts
Pure C inference engine for Qwen3-TTS text-to-speech. No Python, no PyTorch — just C and BLAS....
aahl/qwen-tts2api
🗣️ Qwen TTS to OpenAI Speech API
kapi2800/qwen3-tts-apple-silicon
Run Qwen3-TTS text-to-speech locally on Mac (M1/M2/M3/M4). Voice cloning, voice design, custom...