Google’s tragedy video-generating AI mannequin, Veo 3, can create audio to go together with the clips that it generates.
On Tuesday during the Google I/O 2025 developer conference, Google unveiled Veo 3, which the corporate claims can generate sound results, background noises, and even dialogue to accompany the movies it creates. Veo 3 additionally improves upon its predecessor, Veo 2, by way of the standard of footage it will probably generate, Google says.
Veo 3 is on the market starting Tuesday in Google’s Gemini chatbot app for subscribers to Google’s $249.99-per-month AI Ultra plan, the place it may be prompted with textual content or a picture.
“For the primary time, we’re rising from the silent period of video era,” Demis Hassabis, the CEO of Google DeepMind, Google’s AI R&D division, stated throughout a press briefing. “[You can give Veo 3] a immediate describing characters and an setting, and counsel dialogue with an outline of the way you need it to sound.”
The broad availability of instruments to construct video turbines has led to such an explosion of suppliers that the area is changing into saturated. Startups together with Runway, Lightricks, Genmo, Pika, Higgsfield, Kling, and Luma, in addition to tech giants similar to OpenAI and Alibaba, are releasing fashions at a quick clip. In lots of instances, little distinguishes one mannequin from one other.
Audio output stands to be an enormous differentiator for Veo 3, if Google can ship on its guarantees. AI-powered sound-generating instruments aren’t novel, nor are fashions to create video sound effects. However Veo 3 uniquely can perceive the uncooked pixels from its movies and sync generated sounds with clips routinely, per Google.
Right here’s a pattern clip from the mannequin:
Veo 3 was probably made potential by DeepMind’s earlier work in “video-to-audio” AI. Final June, DeepMind revealed that it was creating AI tech to generate soundtracks for movies by coaching a mannequin on a mix of sounds and dialogue transcripts in addition to video clips.
DeepMind received’t say precisely the place it sourced the content material to coach Veo 3, however YouTube is a powerful chance. Google owns YouTube, and DeepMind previously advised TechCrunch that Google fashions like Veo “might” be educated on some YouTube materials.
To mitigate the chance of deepfakes, DeepMind says it’s utilizing its proprietary watermarking expertise, SynthID, to embed invisible markers into frames Veo 3 generates.
Whereas firms like Google pitch Veo 3 as highly effective artistic instruments, many artists are understandably cautious of them — they threaten to upend complete industries. A 2024 study commissioned by the Animation Guild, a union representing Hollywood animators and cartoonists, estimates that greater than 100,000 U.S.-based movie, tv, and animation jobs will likely be disrupted by AI by 2026.
Google additionally at present rolled out new capabilities for Veo 2, together with a characteristic that lets customers give the mannequin photographs of characters, scenes, objects, and types for higher consistency. The tragedy Veo 2 can perceive digicam actions like rotations, dollies, and zooms, and it permits customers so as to add or erase objects from movies or broaden the frames of clips to, for instance, flip them from portrait into panorama.
Google says that every one of those new Veo 2 capabilities will come to its Vertex AI API platform within the coming weeks.