A powerful, multi-format text-to-speech system that can convert various document formats into audio files.
-
Supports multiple input formats:
- PDF files (.pdf)
- EPUB e-books (.epub)
- Text files (.txt)
- HTML files (.html)
- Markdown files (.md)
- Word documents (.docx)
- Rich Text Format (.rtf)
-
Supports multiple output formats:
- WAV (.wav)
- MP3 (.mp3)
- OGG (.ogg)
-
Parallel processing for faster conversion
-
Progress tracking and status updates
-
Customizable voice profiles
- Make sure you have Python 3.8 or higher installed
- Clone or download this repository
- Install the required dependencies:
pip install -r requirements.txt
To convert a single file:
python run_conversion.py "path/to/your/file.pdf" --voice default --save --format wavTo convert multiple files at once:
python run_parallel_conversion.py--voiceor-v: Select voice profile (default: "default")--saveor-s: Save audio to file--formator-f: Output format (mp3, wav, or ogg)
universal_tts_system/
├── engines/ # TTS engine implementations
├── readers/ # File reader implementations
├── profiles/ # Voice profiles
├── utils/ # Utility functions
├── main.py # Main system implementation
├── run_conversion.py # Single file conversion script
├── run_parallel_conversion.py # Parallel processing script
└── requirements.txt # Project dependencies
- PDF (.pdf)
- EPUB (.epub)
- Text (.txt)
- HTML (.html)
- Markdown (.md)
- Word (.docx)
- Rich Text (.rtf)
- WAV (.wav)
- MP3 (.mp3)
- OGG (.ogg)
-
If you get a "No reader available" error:
- Make sure the file format is supported
- Check if all dependencies are installed
-
If you get a TTS engine error:
- Try using a different voice profile
- Check if your system has the required audio drivers
Feel free to submit issues and enhancement requests!