How it works
Record once
A single sample from the voice that should front your content.
Voice
One voice across a library nobody had time to narrate.
Clone a voice once and narrate every video with it, so a hundred videos made by a dozen people still sound like one person.
One recording of the person who should be narrating.
What Clueso does
Narrates with it
Any script in the workspace can be read in that voice.
What you get
One voice, whoever made the video
The library sounds deliberate instead of assembled.
What it actually does
The controls an evaluator asks about, not a restatement of the headline.
Reusable across the workspace
A cloned voice is available to projects, not locked to the one it was made in.
Paired with a pronunciation dictionary
Product names and acronyms get said correctly, every time, in that voice.
Works with the translation path
Narration and localisation run through the same pipeline.
Re-render instead of re-record
A script change is a render, not a calendar invite with the person who recorded it.
Without it
With Voice cloning
Without it
Every video sounded like whoever happened to record it, and fixing a line meant finding that person again.
With Voice cloning
The voice is a property of the workspace. A script change is a re-render.