Voice Studio
AI-generatedVoice Studio
Design a voice from text, clone from a sample, tune stability and similarity, then use it for TTS, voice changing, and dubbing.
Introduction
The Voice Studio is where your model learns to speak. You can design a voice from a text description, clone one from an audio sample, fine-tune it, and then use it across text-to-speech, voice changing, and dubbing.
How to Use
AI-generatedCreate or clone a voice
Design a voice by describing its tone (warm, bright, authoritative), or clone from an audio sample. Cloning requires voice consent.
Stability & Similarity sliders
Tune stability and similarity
Adjust the sliders to balance consistency (stability) vs. expressiveness (similarity). Higher stability = more uniform; higher similarity = closer to the source.
AI-generatedUse it everywhere
Once attached, the voice powers text-to-speech (2 credits per line), the voice changer, and multilingual dubbing.
2 credits per line
Text-to-speech costs 2 credits per voiceover line — making it affordable to generate many variations of a script.
Video Guide
Full walkthrough video coming soon
Samples
See what this tool creates
AI-generatedSample 1
AI-generatedSample 2
AI-generatedSample 3
