Transform English podcasts into Mandarin Chinese while preserving speaker tone, style, and content.
- Accurate Transcription: Advanced ASR with speaker diarization
- Speaker Analysis: Identify unique voice characteristics of each host
- Cultural Adaptation: Translate content with cultural context preserved
- Voice Matching: Generate Mandarin TTS voices that match original hosts
- Timing Synchronization: Maintain natural flow and pacing
- Python 3.8 or higher
- API keys for OpenAI and ElevenLabs
- Clone this repository
- Create a virtual environment:
python -m venv venv - Activate the environment:
- Windows:
venv\Scripts\activate - macOS/Linux:
source venv/bin/activate
- Windows:
- Install dependencies:
pip install -r requirements.txt - Create a
.envfile with your API keys: