README.md

metadata

title: VideoVoice Translate
emoji: 🎬
colorFrom: purple
colorTo: blue
sdk: gradio
sdk_version: 5.49.1
app_file: app.py
pinned: false
license: mit
sdk_variant: zerogpu

🎬 Video Voice Translator

Translate videos to different languages while preserving the original voice characteristics using AI voice cloning!

Features

• 🎙️ Voice Cloning: Preserves the original speaker's voice characteristics
• 🌍 Multi-language Support: Translate to multiple languages
• 🚀 GPU Acceleration: Automatically uses GPU when available (including ZeroGPU on Hugging Face Spaces)
• 📝 Transcription & Translation: View detailed transcription and translation

Technology Stack

• faster-whisper: Fast and accurate speech transcription
• Google Translate: Translation engine
• Chatterbox TTS: Advanced voice cloning and text-to-speech
• Gradio: User-friendly web interface

Usage

1. Upload a video file
2. Select the target language
3. Click "Start Translation"
4. Wait for processing (progress will be shown)
5. Download your translated video!

Deployment

Hugging Face Spaces (ZeroGPU)

This app is optimized for Hugging Face Spaces with ZeroGPU support. The app will automatically:

• Detect and use GPU when available
• Apply ZeroGPU decorators for efficient GPU allocation
• Fall back to CPU if GPU is not available

Local Development

# Install dependencies
pip install -r requirements.txt

# Run the app
python app.py

The app will automatically detect if you have a CUDA-capable GPU and use it for faster processing.

Configuration Reference

Check out the Hugging Face Spaces configuration reference for more details.