Open-Source Qwen3 Audiobook Converter: Turns PDFs and EPUBs into Cloned Voice Audio
tom_doerr · x · 2026-08-06
Developer WhiskeyCoder has released Qwen3-Audiobook-Converter, an open-source tool based on the Qwen3 TTS voice model.
Key Features:
- Multi-Format Support: Converts TXT, PDF, EPUB, DOCX, and DOC files into high-quality speech.
- Dual Voice Modes: Offers pre-built, optimized narrator voices (Ryan, Serena, etc.) and supports voice cloning from reference audio samples with automatic transcription.
- Smart Processing: Features intelligent text chunking with sentence boundary detection and caching to avoid reprocessing identical text chunks.
- Model: Utilizes a 1.7B parameter TTS model for optimal results.
The project has currently garnered over 870 stars on GitHub.
More from coding & agent
- a16z on Loop Engineering: Designing Termination Conditions for AI Agents — stuffyokodraws · 2026-08-07
- AgentGUI Preprint: Humans Understand Agent Traces 38% Faster — Michael_D_Moor · 2026-08-07
- Diagnosing Agent Reward Hacking: Fixing Poor Signal-to-Noise Ratios — doodlestein · 2026-08-07
- Open-Sourcing a Multi-Agent Adversarial AI Pipeline for Medical Data Analysis — JWojoMojo · 2026-08-07
- Empowering Agentic Systems with Temporal: What Does Durable Execution Fix? — heyneighbor · 2026-08-07
- OpenAI Launches Agent Plugins Open Standard with Cursor, GitHub — OpenAIDevs · 2026-08-07