Google’s artificial intelligence unit, DeepMind, announced its artificial intelligence tool that will voice videos produced by artificial intelligence. However, the results are not very good so far…
Google’s artificial intelligence research laboratory DeepMindhas announced a new tool that voices AI-generated videos called V2A (short for “audio from video”). According to DeepMind’s statement V2AWhile creating the sounds, it uses both the written description and analyzes the video pixel by pixel. In this way, it can create sound even if you do not write a description.
It must be said that artificial intelligence tools are important in dubbing the video. Because although there are many artificial intelligence tools today that can create videos from text or images, these tools are It can produce mostly silent videos. However, we all know that video is a type of media that is audio as well as visual. When we see a video of a fast moving train, the video loses its effect when we cannot hear the sound of the rails, wagons and locomotive.
Example of V2A voicing an AI-generated guitar playing video
DeepMind claims that V2A is unbeatable in terms of producing video-compatible audio and automatically synchronizing audio with the image. However, when we look at the examples shared, it is difficult to say that we are impressed. V2Aproduces sound that matches the picture, but seems more like dubbing a stock sound that matches the picture.
The examples below show how far V2A has yet become when it comes to dubbing videos. primitive It may help you understand what’s left. However, it should not be forgotten that Dall-E once drew a fuzzy yellow ball when asked to draw a canary. Artificial intelligence tools improve as you use them…