Store

A multi-voice AI audiobook generator built on Qwen3-TTS — annotate scripts with an LLM, assign unique voices to each character, per-line style instructions for delivery, clone voices from reference audio, design new voices from text descriptions, train custom voices with LoRA fine-tuning, and export to MP3 or Audacity multi-track projects

Local-first audiobook production with cloned voices, chapter-based editing, segment regeneration, narrator + character casting, and final export in one web app. XTTS runs fully local by default. Voxtral is available as an optional cloud voice path with your own Mistral API key if you want another engine for specific voices. Voice profiles can use different engines in the same project, so you can mix narrator and character workflows without leaving Audiobook Studio. Built for iterative production: preview voices, regenerate only changed sections, queue chapter or segment work, and assemble the finished audiobook when everything is ready. Note: enabling Voxtral sends synthesis text and selected reference audio to Mistral. Learn more: https://senigami.github.io/audiobook-studio/