VoxWild

VoxWild runs offline on Windows for text-to-speech, with 13 voices, cloning from short recordings and batch generation.

voxwild.com
VoxWild homepage screenshot

About VoxWild

VoxWild is a Windows desktop app for text-to-speech. It provides 13 voices, voice cloning from short recordings, AI enhancement, and a batch queue, with Fast and Natural engines and speed control.

It runs on Windows 10/11 64-bit without an account and processes text and audio on the device, except for a license check via Gumroad and a daily version check via GitHub. The Free tier includes unlimited Fast mode with 3 Natural mode and 3 Enhancement uses, and the installer is unsigned, which triggers a SmartScreen warning.

Key features

  • 13 built-in voices for text-to-speech generation
  • Voice cloning from 6-second reference recordings
  • Fast and Natural engines with adjustable speed
  • Batch queue for multiple synthesis jobs
  • AI enhancement for generated speech audio
  • On-device processing except license and update checks
Best for: Windows users who need offline text-to-speech with short-sample voice cloning and batch generation.
Good for
  • Processes text, audio and voice clones on the computer, aside from license and update checks
  • Allows commercial use on every tier, subject to watermark and voice-rights requirements
  • Free tier includes unlimited Fast mode text-to-speech
Watch out for
  • Windows 10/11 64-bit only; installer is about 377 MB
  • Installer is unsigned and triggers a SmartScreen warning
  • Free tier limited to 3 Natural mode and 3 Enhancement uses

VoxWild at a glance

Type
Online tool
Pricing
Free
Platforms
Web, Windows
Open source
Not stated
Language
English
Last checked
Oct 5, 2026 · Online when checked
Listed
Oct 5, 2026

VoxWild alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 16 alternatives

Popular in AI Voice Cloning

Well-known listings from the same topic.

All 17

VoxWild FAQ

Does it actually run offline?
Yes, except for a Gumroad license check when entering a key and a daily GitHub version check. Text, audio and clones do not leave the computer.
Can I use the audio commercially?
Yes, on every tier including Free for both engines. Chatterbox output includes an inaudible neural watermark, and you must only clone voices you have rights to clone.
How good is 6-second voice cloning?
It can work in a podcast context but not for fooling someone who knows the voice well. Longer 30-60 second clean samples produce better results, and clean short audio is better than noisy long audio.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing