Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Convert PDFs, EPUBs, DOCX, DOC, and TXT files into high-quality audiobooks using **Qwen3 TTS Voice Model** - an open-source voice synthesis system that excels at natural speech generation and voice cloning.
| Date | Stars |
|---|---|
| 2026-08-03 | 871 |
| 2026-08-06 | 871 |
| 2026-08-12 | 1055 |
| 2026-08-18 | 1069 |
| 2026-08-19 | 1072 |
| 2026-08-20 | 1075 |
| 2026-08-21 | 1078 |
| 2026-08-23 | 1079 |
| 2026-08-24 | 1081 |
| 2026-08-27 | 1085 |
| 2026-08-31 | 1086 |
| 2026-09-03 | 1088 |
| 2026-09-05 | 1089 |
| 2026-09-07 | 1090 |
| 2026-09-08 | 1091 |
| 2026-09-09 | 1090 |
| 2026-09-10 | 1091 |
| 2026-09-11 | 1092 |
| 2026-09-19 | 1093 |
| 2026-09-20 | 1094 |
| 2026-09-24 | 1095 |
| 2026-09-25 | 1096 |
| 2026-09-26 | 1097 |
| 2026-09-28 | 1096 |
| 2026-09-30 | 1097 |
| 2026-10-02 | 1102 |
| 2026-10-03 | 1102 |
| 2026-10-04 | 1103 |
| 2026-10-06 | 1105 |
| 2026-10-11 | 1104 |
| 2026-10-12 | 1102 |
| 2026-10-13 | 1103 |
| 2026-10-14 | 1104 |
| 2026-10-15 | 1106 |
| 2026-10-20 | 1107 |
| 2026-10-23 | 1106 |
| 2026-10-24 | 1108 |
| 2026-10-25 | 1109 |
| 2026-10-26 | 1110 |
| 2026-10-29 | 1111 |
| 2026-10-30 | 1112 |
| 2026-11-02 | 1113 |
| 2026-11-04 | 1113 |
Today
— stars today
This week
+3 stars this week
This month
+10 stars this month
Momentum
0.0
growth rate 0.27%/day
# 🎧 Qwen Audiobook Converter [](https://www.python.org/downloads/) [](LICENSE) [](https://github.com/QwenLM/Qwen3-TTS) Convert PDFs, EPUBs, DOCX, DOC, and TXT files into high-quality audiobooks using **Qwen3 TTS Voice Model** - an open-source voice synthesis system that excels at natural speech generation and voice cloning. ## ✨ Features - 🎤 **Dual Voice Modes** - **Custom Voice**: Pre-built high-quality speakers (Ryan, Serena, Aiden, etc.) with optimized audiobook narration style - **Voice Clone**: Clone any voice from a reference audio sample with automatic transcription - 📚 **Multi-Format Support**: TXT, PDF, EPUB, DOCX, DOC - 🤖 **Always 1.7B Model**: Uses the highest quality model for best results - 🔄 **Smart Chunking**: Intelligent text splitting with sentence boundary detection - 💾 **Intelligent Caching**: Avoids re-processing identical chunks - 🔁 **Robust Error Handling**: Automatic retries and graceful failure recovery - 📊 **Progress Tracking**: Real-time conversion progress with time estimates - 🧹 **Auto Cleanup**: Automatic cleanup of temporary files, even on failure ## 🔊 Audio Demo 🎧 **Sample Output** <figure> <figcaption>Listen to the T-Rex:</figcaption> <audio controls src="https://github.com/WhiskeyCoder/Qwen3-Audiobook-Converter/blob/main/sample/test_audio.mp3"></audio> <a href="https://github.com/WhiskeyCoder/Qwen3-Audiobook-Converter/blob/main/sample/test_audio.mp3"> Download audio </a> </figure> No it's not broken, it's a raw mp3 file download it and play it, you can't embedded audio in a readme.md GitHub whenthe sample is on GitHub ## 🚀 Quick Start ### Prerequisites 1. **Qwen Voice Model** running locally - Download and run the Qwen3 TTS Gradio interface (One Click install with Pinokio) - Server should be accessible at `http://127.0.0.1:7860` 2. **Python 3.8+** with pip 3. **FFmpeg** - Required for audio processing ### Installation 1. **Clone the repository**: ```bash git clone https://github.com/WhiskeyCoder/Qwen3-Audiobook-Converter.git cd Qwen3-Audiobook-Converter ``` 2. **Install Python dependencies**: ```bash pip install -r requirements.txt ``` 3. **Install FFmpeg**: - **Windows**: Download from [ffmpeg.org](https://ffmpeg.org/download.html) or `choco install ffmpeg` - **Linux**: `sudo apt-get install ffmpeg` - **macOS**: `brew install ffmpeg` 4. **Start Qwen Voice Model**: - Run your Qwen Gradio interface - Verify it's accessible at `http://127.0.0.1:7860` 5. **Add your books**: ```bash # Place your books in the book_to_convert folder cp your_book.pdf book_to_convert/ ``` 6. **Run the converter**: ```bash # Default: Custom Voice mode (Ryan speaker, English) python audiobook_converter.py # Voice Clone mode with automatic transcription python audiobook_converter.py --voice-clone --voice-sample path/to/reference.wav ``` ## 📋 Requirements ### Python Dependencies ``` gradio_client>=0.7.0 requests>=2.28.0 PyPDF2>=3.0.0 ebooklib>=0.18 pydub>=0.25.1 python-docx>=0.8.11 docx2txt>=0.8 beautifulsoup4>=4.11.0 ``` ### System Requirements - **Python**: 3.8 or higher - **FFmpeg**: Required for audio processing (install separately) - **Qwen Voice Model**: Running locally with Gradio API enabled - **RAM**: 4GB+ recommended - **Storage**: ~100MB per hour of audiobook ## ⚙️ Configuration ### Hardcoded Settings The converter uses optimized hardcoded settings for best audiobook quality: - **Speaker**: Ryan (professional male narrator) - **Language**: English - **Model Size**: 1.7B (always - highest quality) - **Input Folder**: `book_to_convert/` - **Output Folder**: `audiobooks/` - **Style Instruction**: Optimized for engaging, professional audiobook narration ### Voice Modes #### Custom Voice Mode (Default
Excerpt of 11,619 characters
Read on GitHub
15
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:586c89ed938b114a, desc:voice cloning, desc:voice synthesis