Among the many tech advancements unveiled at Google Cloud Next include a major generative media upgrade to Vertex AI, Google Cloud’s managed AI development platform. The new Vertex AI Media Studio lets enterprise users generate complete videos from scratch using text prompts. Lyria, Google’s text-to-music model is now available on Vertex in private preview. Both are subject to an “allowlist.” Chirp 3 now creates custom voices with just 10 seconds of audio input, while Imagen 3 has gained improved abilities for reconstructing missing or damaged portions of an image.

Vertex AI Media Studio “bundles together several of the company’s advanced models to handle every aspect of video production, including visuals, voice, and music, without needing any video editing or coding experience,” reports Android Authority.

Google Cloud explains in a blog post that the updates “make Vertex AI the only platform with generative media models across video, image, speech and music.”

Users can get started by generating an image using Googe’s image generator, Imagen 3. “That image can then be transformed into a video using Veo 2, the company’s video generation model, which also offers customization tools,” Android Authority says, citing the addition of robust new editing tools for Veo 2.

These include inpainting and outpainting as well as sophisticated cinematic features that allow directed shot composition, camera angles and pacing “without requiring complex prompting or specialized expertise,” according to Google.

“Veo 2 can now automatically remove objects, expand videos, and apply cinematic style presets,” writes The Verge, which says the improvements allow Veo 2 users “make cinematic-looking generations and edit real footage.” Among the Veo 2 improvements: camera pre-sets guide movement in different directions, and timelapse effects are possible, as are drone-style shots.

Veo 2 even offers interpolation, which lets you join two assets to define the beginning and end of a video sequence, with Veo generating the intervening frames.

PetaPixel says the new editing tools “are designed to give users more control over cinematic style and editing in both AI-generated and real-world footage.”

“Once the visuals are ready, Media Studio uses Chirp, Google’s voice synthesis model, to add a voiceover,” Android Authority points out, adding that “Lyria — a model jointly developed by Google DeepMind and YouTube — generates a music track to serve as the background score” for the finishing touch.

“In theory, the result is a complete, ready-to-share video that looks and sounds professional,” notes Android Authority, emphasizing “all of this can be done from a single workspace in the Vertex AI Studio, the same console where developers can test Google’s latest Gemini models.”