TLDR: YouTube has unveiled a comprehensive suite of generative AI tools for creators, particularly enhancing its Shorts platform. These innovations, powered by Google DeepMind’s Veo 3 and Lyria 2 models, enable creators to generate videos from text prompts, transform dialogue into unique songs, animate still photos, apply artistic styles, add objects to scenes, and automatically produce first drafts of videos from raw footage. The goal is to make content creation more accessible, playful, and efficient, with a commitment to transparency through AI content labeling.
At its annual ‘Made on YouTube’ event on September 16, 2025, YouTube announced a significant expansion of its creative toolkit, introducing a powerful array of generative AI features designed to empower creators, especially within its Shorts ecosystem. These updates are poised to transform how millions produce content, making the creative process more intuitive and less labor-intensive.
Central to these advancements is Veo 3 Fast, a custom version of Google DeepMind’s Veo 3 video generation model. This tool allows creators to generate 480p video clips with accompanying sound directly from text prompts, offering a seamless and low-latency experience within the YouTube app. It is currently rolling out in the United States, United Kingdom, Canada, Australia, and New Zealand, with plans for broader global availability.
Another groundbreaking feature is Speech to Song, powered by Google DeepMind’s advanced Lyria 2 music model. This innovative tool can convert dialogue from eligible videos into catchy, customizable soundtracks. Creators can even select a desired ‘vibe’ for the song, such as ‘chill,’ ‘danceable,’ or ‘fun,’ ensuring the original creator is always attributed.
YouTube is also introducing several new Veo capabilities for Shorts aimed at enhancing visual creativity:
Add Motion: This feature allows creators to bring still photos to life by capturing and transferring movement from another video, enabling dynamic animations from static images.
Stylize your video: Creators can apply artistic filters, such as pop art or origami, to their footage with a simple tap, completely transforming the visual aesthetic.
Add Objects: Users can insert characters, props, or effects into their scenes using straightforward text descriptions.
To streamline the initial stages of video production, YouTube is launching Edit with AI. This feature tackles the daunting task of starting from a blank timeline by intelligently analyzing raw camera roll footage. It identifies and arranges the best moments, adds appropriate music and transitions, and can even generate a reactive voiceover in English or Hindi, providing creators with a compelling first draft to personalize.
Dina Berrada, YouTube’s Director of Product for Shorts and Generative AI Creation, emphasized the platform’s role, stating, ‘As the world’s largest creative playground, YouTube is where trends are born and where you can draw inspiration from.’ These tools are designed to lower barriers to entry and foster new forms of storytelling.
Also Read:
- Krotos Unveils AI-Assisted ‘Video to Sound’ for Automated Audio Sync at IBC 2025
- Wix Fortifies Market Leadership with Extensive AI Innovations and Strong Financial Performance
YouTube is also committed to responsible AI implementation. All content generated using these new AI tools will be clearly marked with SynthID watermarks and content labels, ensuring transparency for viewers. The rollout of these features positions YouTube strategically in the competitive short-form video market, aiming to attract and retain creators by offering unparalleled AI-powered creative capabilities.
