- Input
A short reference clip — about three seconds is usually enough
- Where
On your machine — the desktop app runs without an account
- Reuse
Cast a cloned voice in stories, audiobooks, and dubbing
Hear rendered voices
Prerecorded renders from the desktop app — static evidence, not a live demo.
Three renders
Cinematic narration
“The valley had been quiet for a hundred years, and tonight, for the first time, something stirred beneath the old stone bridge.”
femalemiddle-agedlow pitchBritish accent
0:00 / 0:06
Ready: The Librarian
Designed from one prompt, rendered locally. Source
- Workflow
- Voice design text to speech
- Engine
- VoiceStudio OmniVoice local engine
- Render
- 24 kHz mono MP3, 0:06
- Origin
- Rendered locally in VoiceStudio; served as bundled same-origin static media.
Full provenance
- Version disclosure
- A model-weight version was not preserved in the original export; the renderer export is pinned below.
- Post-processing
- Mono MP3 export. No additional mastering was disclosed in the original export record.
- Source permission
- Original synthetic voice design with no human voice recording or visitor media.
- Evidence revision
- 7d2b2eb6692fce59be82cdf9494349a8e9dc3c90
Free · open source · AGPL-3.0
Download VoiceStudio
fully-local voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages
DownloadmacOS · Windows · Linux · Docker