VoxForge
Turn any ebook into a multi-voice audiobook.
Upload an epub or txt, let VoxForge auto-cast each character, assign a distinct voice, and render a full, chaptered audiobook you can stream and export. Unlimited rendering — no per-character subscription.
- NarratorThe lighthouse keeper had not spoken to anyone in three weeks.
- Mara"You came back," she said, almost to herself.
- Eli"I said I would. I keep my word."
- NarratorAt dawn, the sea moved in a steady rhythm.
A recording studio for your book
Everything you need to take a manuscript from text to a finished, multi-voice audiobook.
Auto character casting
Drop in an ebook and VoxForge detects the narrator and each speaking character, so you can cast a distinct voice per role.
Multi-voice rendering
Assign a warm, human-sounding voice to every character and render the whole book in one pass — narrator and full cast.
Chapter render queue
Watch each chapter render with live progress, play finished chapters while later ones render, and resume right where you left off.
English, Chinese & Japanese
Natural narration across EN, ZH and JA — surface-quality voices for fiction, light novels and web novels alike.
Voice cloning
Upload 10-30 seconds of reference audio to create a reusable custom voice, then reuse it across any book.
Stream & export
A real scrub-able player with chapter markers, plus one-click export to mp3 or chaptered m4b.
Pricing
Built for people tired of paying a subscription per character. Buy once, render forever.
Free
Hear the multi-voice effect
- First chapter of every book
- All preset voices (English / 中文 / 日本語)
- Download the rendered mp3
Pro
Unlimited rendering, monthly
- Unlimited books & characters
- Unlimited rendering, no caps
- Cancel any time
- mp3 download for every chapter
Lifetime
Pay once, render forever
- Everything in Pro, forever
- No monthly subscription
- All future voices included
- Email support
Frequently asked questions
Everything you need to know before you start rendering.
From the studio
Guides on audiobook production, multi-voice casting, and getting the best narration quality.
Sub-50ms TTS: What It Means for AI Audiobook Generators
Explore how sub-50ms text-to-speech latency transforms ebook to audiobook workflows. Learn why speed matters for multi-voice narration and character casting.
Elena AshfordSpeko Routes Voice Models. Audiobooks Still Need a Studio
YC S26 Speko is OpenRouter for STT, LLM, and TTS. For ebook-to-audiobook work, a router picks providers; it does not cast characters or pass ACX checks.
Elena AshfordAudiobook Narration Pacing: A Scene-by-Scene Guide
Direct audiobook pace with meaning, syntax, pauses, character contrast, scene energy, and repeatable listening tests instead of one target speed.
Elena AshfordReady to hear your book?
Upload a chapter, cast your characters, and render a multi-voice audiobook in minutes. Start free — no subscription required.