Lukas1h/mimic3

A fast local neural text to speech engine for Mycroft

Mimic 3

A fast and local neural text to speech system developed by Mycroft for the Mark II.

• Available voices
• Documentation
• How does it work?

Quickstart

Mycroft TTS Plugin

# Install system packages
sudo apt-get install libespeak-ng1

# Ensure that you're using the latest pip
mycroft-pip install --upgrade pip

# Install plugin
mycroft-pip install mycroft-plugin-tts-mimic3[all]

# Activate plugin
mycroft-config set tts.module mimic3_tts_plug

# Start mycroft
mycroft-start all

See documentation for more details.

Web Server

mkdir -p "${HOME}/.local/share/mycroft/mimic3"
chmod a+rwx "${HOME}/.local/share/mycroft/mimic3"
docker run \
       -it \
       -p 59125:59125 \
       -v "${HOME}/.local/share/mycroft/mimic3:/home/mimic3/.local/share/mycroft/mimic3" \
       'mycroftai/mimic3'

Visit http://localhost:59125 or from another terminal:

curl -X POST --data 'Hello world.' --output - localhost:59125/api/tts | aplay

See documentation for more details.

Command-Line Tool

# Install system packages
sudo apt-get install libespeak-ng1

# Create virtual environment
python3 -m venv .venv
source .venv/bin/activate
pip3 install --upgrade pip

pip3 install mycroft-mimic3-tts[all]

Now you can run:

mimic3 'Hello world.' | aplay

Use mimic3-server and mimic3 --remote ... for repeated usage (much faster).

See documentation for more details.

---

License

Mimic 3 is available under the AGPL v3 license