Slide 1
![](/static/images/home_logo.png)
SYSTEM ARCHITECTURE
This is the Voice box technology which is coming form Facebook (Meta AI).
its a text to speech model
- Generate Voice: with minimal voice input of 2 seconds we can generate the voice for any text
- Style Transfer: We can use the voice style from an audio and generate the new audio
it can generate the natural voice based on the new input text
- Audio erasing: You can remove any back ground noice
- Examples are mentioned in this
This can be best tool for the Voice Dubbing technology
![](/static/images/home_logo.png)