metadata
title: Mockingbird
app_file: app.py
sdk: streamlit
python_version: 3.11
pinned: false
Mockingbird TTS Demo
This repo hosts Mockingbird, a demo of open Text-to-Speech tools.
Currently, 3 synthesizers are supported:
- Meta's Massively Multilingual Speech (MMS) model
- Coqui's TTS package and the models supplied via that
- ESpeak-NG's synthetic voices
Voice conversion is achieved through Coqui.
Notes:
- ESpeak-NG seems to have the worst performance out of the box, but it has a lot of options for controlling voice output.
- Coqui is no longer being officially developed.
- Where a synthesizer supports multiple models/voices, I manually pick the appropriate model.
- Not all synthesizers support a given language.