The new AI features will be added gradually within months and will be available in selected countries.
YouTube is releasing a new set of artificial intelligence tools for Shorts content creators. The company revealed the AI tools during its Made on YouTube live event.
The company will add a customized version of Google’s Veo 3 video creation AI model. In addition, a new AI editing feature and a remixing tool will be added among other AI tools.
Veo 3 merges with YouTube Shorts
According to a blog post from YouTube, the video-sharing platform has partnered with Google’s DeepMind to create a custom version of Veo 3. The new version of the popular video generation model, which will merge with YouTube, is called Veo 3 Fast.
The fast version of Veo 3 will generate videos using text. The videos will have a resolution of 480p and lower latency, making it easier for creators to make clips. YouTube announced that adding sounds to such clips will be possible for the first time ever.
Veo 3 Fast will make it possible to animate images using a video. For example, creators can animate an image of a person to make athletic movements or even dance. This is done by extracting the movements from a real video.
Short creators can also add objects to the AI-generated video, like a character, prop, or even a specific effect, only through text. YouTube said this feature will open up “even more creative possibilities for what you can make next.” A good example is adding a “add a rubber ducky to your morning coffee.”
Moreover, the AI tools will enable content creators to transform a video by adding new styles like pop art or origami, giving the video a new and fresh look.
The new set of AI tools will be available for YouTube Shorts creators in the upcoming months.
Remix speech into new soundtracks
Another exciting tool is the Speech to Song remixing tool. Adding a quote, a funny dialogue, or a unique sound to a video is possible through this tool, making content more fun and engaging. Content creators get to choose their favorite sound from eligible videos and turn it into a soundtrack.
Dina Berrada, the Director of Product, Shorts and Generative AI Creation at YouTube, said, “As the world’s largest creative playground, YouTube is where trends are born and where you can draw inspiration from. Imagine hearing a line of dialogue that sparks an idea — a funny phrase, a memorable quote, or a one-of-a-kind sound — and you want to remix it into a new sound.”
Speech to Song remixing tool is powered by Lyria 2, Google DeepMind’s most advanced AI music model. Lyria 2 will use the dialogue from a video and turn it into a song. Users get to choose from several sound styles like “chill, danceable, or fun.”
YouTube will start testing the remixing tool soon and will begin rolling it out in the United States within weeks.
Edit with AI transforms raw footage
Another feature to be released soon is Edit with AI. This feature will transform raw footage into a first draft by looking for the moments and arranging them. The tool will add music, transitions, and “even a playful voiceover that can react to what’s happening in the video.” The voice-over will be in English and Hindi.
YouTube clarified that it’s still in the experimenting stage. Edit with AI will be available on Shorts and in the YouTube Create app within the upcoming weeks.
The company added that the set of new AI tools will be available in selected jurisdictions, including the United States, the United Kingdom, Canada, Australia, and New Zealand. The company will expand the new set of AI tools to other countries in the future.
Your crypto news deserves attention – KEY Difference Wire puts you on 250+ top sites
