Mimic 3
Privacy-focused neural TTS engine by Mycroft AI for offline voice assistants.
About
Mimic 3 served as the voice of Mycroft AI's Mark II smart speaker: a fast, fully offline neural text-to-speech engine built for privacy-focused voice assistants on modest hardware such as the Raspberry Pi. It runs locally with low latency, offers a command line tool, a web server on port 59125, and Docker images, and supports a range of languages and voices distributed through a companion repository. The engine is open source under the AGPL-3.0 license. The project is no longer actively maintained, and the repository points to Piper TTS, from the same developer, as its spiritual successor carrying the same offline, low-resource philosophy forward. Mimic 3 still works and remains of interest to hobbyists running legacy Mycroft setups or studying compact neural TTS design, but new voice assistant projects generally start with Piper instead.
Should you use Mimic 3?
Pick it when
Pick Mimic 3 only when you maintain a legacy Mycroft setup or Mark II device that already depends on its voices and its port 59125 web server, and you need fully offline speech on a Raspberry Pi class board.
Look elsewhere when
Skip it for anything new: the project is no longer maintained, its own repo points to Piper as the successor, and AGPL-3.0 adds network copyleft obligations if you serve it to users. Start with Piper instead.
Alternatives to Mimic 3
- Piper TTS
Its named successor from the same developer, now under the Open Home Foundation with a C and C++ library and voice training, so new offline assistant work belongs here.
- Sherpa-ONNX TTS
Runs Piper and other models offline on far more platforms, including Android, iOS, and WebAssembly, with bindings in a dozen languages, under Apache-2.0.
- eSpeak NG
Tiny formant synthesizer with 100+ languages and no model files, robotic in timbre but runs on hardware too weak for any neural engine.
- Kokoro TTS
82M model with Apache-2.0 weights and streaming output on CPU, a better pick when your device is a PC or small server rather than a Pi.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Text-to-Speech (TTS)
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- AGPL-3.0
- Added
- Apr 3, 2026