Audiobook & Script Production

Keep your performance,
swap your voice.

Record once in your own voice. Voxxen™ converts each line into a different character — instantly, offline, on your machine.

Download for Windows See how it works

From your voice to a full cast

Listen to a sample
One voice. Full cast.
01

Set Up Your Cast

Create characters, assign voice models, and color-code your cast. Voxxen parses your script and maps every line automatically.

02

Record Your Performance

Record the entire chapter in one take. Switch active characters with a hotkey as you go — Voxxen tracks every segment.

03

Convert & Tune

One click converts your recording into individual character voices. Fine-tune pitch, formant, and character using the built-in voice tuner.

04

Export Stems

Get clean, per-character WAV stems ready for your DAW. 24-bit, 48kHz. Production-ready out of the box.

Built for producers,
not hobbyists.

Every feature was designed around a real audiobook production workflow.

One-Take Recording

Record an entire chapter of your book or Act of your screenplay yourself as different characters.

70 Unique Voice Models

A professionally trained library spanning age 11 to 71, American, British, Scottish, Irish, Welsh, Canadian, European, and Indian accents.

Live Voice Tuner

Record a 5-second test clip, then dial in pitch, formant ratio, and index rate in real time until the character sounds exactly right.

Novel & Screenplay Support

Import a PDF. Voxxen parses dialogue, assigns it to your cast, and organizes everything by chapter or act.

Fully Offline

No internet connection after setup. No cloud processing. Your audio and your projects never leave your machine.

Clean Stem Export

Export per-character 24-bit WAV stems, ready to drop into any DAW. One file per character, perfectly trimmed.

🎭

Character Library

Save tuned characters — name, role, archetype, and all settings — to a personal library. Bring any character into a new project in one click, pre-configured and ready to record.

Voice models are the clay.
You're the sculptor.

Voxxen is not a voice cloner. It's a character creation tool. The included voice models are neutral raw material — gender, age, accent. What makes a character is what you bring to it.

🎙

Your Performance

Record in your own voice. Timing, emotion, pacing, and energy carry through conversion unchanged. That delivery is entirely yours — the voice model only changes the timbre.

🎚

Your Tuning

The Voice Tuning panel lets you dial in pitch, formant, and character weight. Two performers using the same voice model will produce completely different results. The creative choices are yours.

🎭

Your Character

The result is a wholly original character voice — not a copy of anyone. It exists because you made creative decisions. Voxxen is the instrument. The character is your work.

🎭

Character Library — Build a roster that travels with you

Tune a character once, then save their name, role, archetype, and tuning settings to your personal Character Library. Add them to any future project instantly, with all settings pre-loaded. A narrator you built for one audiobook can be used as a character in the next. Or vice versa.

A full cast, day one.

Every voice model is independently trained at 48kHz. No pitch-shifted duplicates — each model is a distinct speaker.

70+
Unique Models
100s
of Possible Characters
48k
Sample Rate
American British RP Scottish Irish Welsh Northern Irish Canadian European Indian Age 11–71 Male & Female Children to Elders

Own it. No subscriptions.

One app, two tiers. Start with Voxxen standard — upgrade to Pro when you're ready to train your own voices.

Coming Soon
Voxxen Pro™
Pricing TBD
For studios & publishers
  • Everything in Voxxen
  • Train your own voice models
  • Import custom voice datasets
  • Voice model management
  • Unlimited voice library
  • Priority support
Notify Me

$149 is for the Voxxen software. A starter voice pack is available as a free download on first launch.

Windows + NVIDIA GPU recommended

Voxxen runs on Windows 10/11. An NVIDIA GPU (RTX series) is strongly recommended — voice conversion is GPU-accelerated. Requires ~27 GB disk space. Mac support coming in v2.

Ready to build your cast?

Download Voxxen and produce your first chapter today.

Download for Windows — Free Trial
System Requirements
OS
Windows 10 / 11 (64-bit)
GPU
NVIDIA GTX 1060 or newer
RAM
16 GB recommended
Disk
~27 GB free space
VRAM
6 GB minimum
Download
~20 GB

NVIDIA GPU recommended for fastest conversion  ·  AMD & Intel: CPU mode in v1  ·  Mac coming in v2