Hendra, a new AI-generated voiceover video tool, has been launched. It’s publicly accessible and allows you to create beautiful AI-generated voiceovers over any portrait image you upload.
How does it work? You can submit your text and also add a static image with a face to the generator. As an output, you will receive a video where the character in the image will be pronouncing the text. It works quite well and is super simple. I will probably try to use it more in my content.
It also works with non-photoreal images. However, if I supply my Alien Frien avatar, it would not be able to recognize the face. It has a strict requirement for the image to have a human-like face to be able to animate it. It basically does animation with lip-sync and everything, then produces the AI-generated voiceover.
Try it here 🔥