Spaces:
Running
on
Zero
Running
on
Zero
| 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 | |
| 1. Enter your text in the input box | |
| 2. Optionally add a style description (e.g., "a calm, gentle voice") | |
| 3. Click "Generate Speech" | |
| 4. Listen to or download the generated audio | |
| ## Model | |
| This Space uses the [MiMo-Audio-7B-Instruct](https://huggingface.co/XiaomiMiMo/MiMo-Audio-7B-Instruct) model, a 7B parameter audio language model developed by Xiaomi. |