Make audiobooks with the author’s voice. Produce new content using voices from the past.
Our unique technology changes your voice to that of another person (e.g., a celebrity) while preserving all the subtle detail of how you say what you say.
Listen to sample Inputs and Outputs of our system.
The Real Example is provided as a baseline for quality comparison. It is a recording of the target speaker saying the target phrase. The ideal Output would sound as good as the Real Example but probably not identical to it. Note that the Real Example is not shown to our system at any time.
Dub movies and TV shows with fewer actors, or change actors while keeping the same voice. Add dialog and voiceovers in an actor's voice without the presence of the actor.
Make audiobooks with the author’s voice. Produce new content using voices from the past.
Make your call center speak with one voice, or target different voices at different customers.
Sing karaoke in the voice of the original singer. Speak in your character's voice in video games.
Speak like yourself, again or for the first time.
We use proprietary deep learning (artificial intelligence) techniques to produce high quality synthetic speech. These techniques are related to those used in the latest text-to-speech systems. But speech-to-speech can be more dynamic and emotional than even the best text-to-speech. And speech-to-speech makes the most sense when the content is being generated by a human.
You can also try our low-quality interactive model
(anyone can speak with Obama's voice)