Free: $0 (first chapter of every book, all preset voices, MP3 download). Pro: $39/month (unlimited books, unlimited rendering, monthly billing, cancel anytime). Lifetime: $199 (one-time payment, everything in Pro forever, all future voices included).
Free: all tools with no sign-up or watermark on audio. Pro: $4.99/month, $1.99 for 7-day pass, or yearly plan (price not specified). Pro adds HQ split, removes watermark from videos, and increases transcription limit from 10 to 60 per hour.
Key features
Auto character detection and casting
Multi-voice rendering across English, Chinese, and Japanese
Voice cloning from reference audio
Live chapter render progress tracking
Stream and export to MP3 or M4B formats
Support for EPUB, PDF, and TXT file formats
Unlimited rendering with no per-character caps
Chapter markers and audiobook structure
Split songs into voice, drums, bass and other parts
Slow down songs to 50% speed without changing pitch
Change song key by up to 12 semitones
Loop sections and build speed for practice
Transcribe audio and generate subtitles
Identify song name and show lyrics
Mix parts with individual volume controls
Works on phone and desktop in browser with no app
What makes it different
No per-character subscription fees; unlimited rendering instead
Lifetime buy-once option for complete pipeline ownership
Warm, human-sounding voices built specifically for long-form fiction
Voice cloning and custom voice reuse across multiple books
Built by an experienced audiobook producer with eight years in the field
All processing runs on your device with no file upload to servers
Completely free with no sign-up or watermark on audio
Uses open-source Meta HTDemucs model for splitting
Handles files up to 500MB and 20 minutes long
Works instantly in browser without re-encoding video
VoxForge
Extractune