🚀 Audiobook Creator v1.0 Release 🎧
I'm excited to release Audiobook Creator v1.0 – an open-source tool that transforms books into immersive, multi-voice audiobooks! 📖🔊
✨ Key Features
🎨 Gradio UI App – Create audiobooks effortlessly with an intuitive, user-friendly interface built using Gradio.
📚 M4B Audiobook Creation – Generates M4B-format audiobooks with covers, metadata, and chapter timestamps for seamless playback.
🔄 Multi-Format Input Support – Converts books from various formats (EPUB, PDF, TXT) into clean, structured text.
🔊 Multi-Format Output Support – Exports audiobooks in multiple formats: AAC, M4A, MP3, WAV, OPUS, FLAC, PCM, and M4B.
🐳 Docker Support – Run effortlessly with pre-built Docker images or use Docker Compose for a hassle-free setup.
📝 Text Cleaning – Automatically formats and refines text for a smooth reading and listening experience.
🎭 Character Identification – Uses NLP and LLMs to detect characters and infer their gender, age, and voice attributes.
🎙 Customizable Audiobook Narration – Choose between single-voice or multi-voice narration for dynamic storytelling.
⏳ Progress Tracking – Stay informed with progress bars and execution time indicators for efficient monitoring.
🛠 Open Source & GPL v3 Licensed – Free to use, modify, and contribute! Join the community and enhance the project.
🚀 Turn your books into immersive audiobooks with ease! 🎧
🐳 Docker Image:
You can pull the latest image with (choose cpu/ cuda gpu variant):
docker pull ghcr.io/prakharsr/audiobook_creator_cpu:v1.0docker pull ghcr.io/prakharsr/audiobook_creator_gpu:v1.0For complete instructions on how to run: Goto the Get Started Section
Full Changelog: https://github.com/prakharsr/audiobook-creator/commits/main