A newer version of the Gradio SDK is available:
6.2.0
metadata
title: Voice Acting TTS
emoji: 🎭
colorFrom: blue
colorTo: blue
sdk: gradio
sdk_version: 6.0.0
app_file: app.py
pinned: true
license: mit
python_version: 3.12
short_description: TTS for any emotion, now with non-verbal sounds!
MiMo-Audio Text-to-Speech
A simple text-to-speech interface powered by Xiaomi's MiMo-Audio model.
Features
- Convert text to natural-sounding speech
- Optional style descriptions to control voice characteristics
- Powered by MiMo-Audio-7B-Instruct model
Usage
- Enter your text in the input box
- Optionally add a style description (e.g., "a calm, gentle voice")
- Click "Generate Speech"
- Listen to or download the generated audio
Model
This Space uses the MiMo-Audio-7B-Instruct model, a 7B parameter audio language model developed by Xiaomi.