| --- |
| title: Jerome Voice Generator |
| emoji: 🗽 |
| colorFrom: orange |
| colorTo: yellow |
| sdk: docker |
| pinned: false |
| license: mit |
| --- |
| |
| # 🗽 Jerome Voice Generator |
|
|
| Type anything and hear Jerome say it — straight outta New York. |
|
|
| Uses Edge TTS for base speech generation + RVC (Retrieval-Based Voice Conversion) to transform it into Jerome's distinctive voice. |
|
|
| ## How It Works |
|
|
| 1. **Text → Speech**: Microsoft Edge TTS generates natural-sounding base speech |
| 2. **Voice Conversion**: RVC model trained on Jerome's voice transforms the audio |
| 3. **Output**: You get Jerome reading your text with his signature New York accent |
|
|
| ## Model |
|
|
| Trained with [Applio](https://github.com/IAHispano/Applio) using 2+ minutes of Jerome's audio, 100 epochs on an NVIDIA T4 GPU. |
|
|
| Model weights: [khobster/jerome](https://huggingface.co/khobster/jerome) |
|
|
