Creating high-quality videos has long demanded specialised knowledge in editing, audio mixing, and visual effects. But now, crafting a complete video could be as simple as writing a text prompt. Google has introduced a new tool that aims to make this process seamless for everyone.
The company has launched Vertex AI Media Studio, an innovative generative AI platform that transforms text prompts into complete videos. Designed for users ranging from seasoned content creators to absolute beginners, the tool harnesses the capabilities of Google Cloud’s Vertex AI.
Get Latest Mathrubhumi Updates in English
At the heart of this platform is the integration of several of Google’s advanced AI models. It begins with Imagen 3, the company’s state-of-the-art image generation tool, which converts a text prompt into an initial image. From there, Veo 2, Google’s AI model for video creation, takes over by turning the image into a dynamic video.
Veo 2 offers a range of customisation options. Users can select various camera styles such as drone-like shots or smooth pans. They can also fine-tune the video’s frame rate and duration. If parts of the generated video aren’t to the user’s liking, a Magic Eraser tool — similar to the one available on Google Pixel devices — allows for swift removal of unwanted elements.
Once the video visuals are locked in, the platform employs Chirp, one of Google’s AI voice models, to add a voiceover. To finish the production, background music is generated using Lyria, a model developed by YouTube and Google DeepMind.
All of these features are available within the same workspace, making it possible to produce professional-looking videos from scratch without needing a production team. With this launch, Google is aiming to redefine how people approach video creation, opening the door to new possibilities for content makers across various industries.
