CtrlK
Veo 3 is a video generation model developed by Google DeepMind and announced at Google I/O on May 20, 2025. It is the third major iteration of the Veo family and the first commercially available video generation model to natively produce synchronized audio alongside video in a single generation pass. The audio output includes spoken dialogue with lip-synced characters, sound effects, ambient noise, and background music, all derived from a text prompt. Veo 3 generates clips up to eight seconds at resolutions up to 1080p (with upscaling paths to 4K), running at 24 frames per second with 48 kHz stereo audio output.
The model is accessible through multiple Google platforms: the Flow filmmaking application, the Gemini app, Vertex AI, Google AI Studio, and the Gemini API. Consumer access at launch was restricted to Google AI Ultra subscribers in the United States at $249.99 per month. Veo 3 was later updated to Veo 3.1 in October 2025, which introduced reference image support, scene extension tools, enhanced audio fidelity, and a "Fast" tier variant optimized for speed and lower cost.
The first version of the Veo model was announced at Google I/O in May 2024. Google DeepMind described Veo 1 as capable of generating 1080p video clips over a minute in length from text or image prompts. The model supported a range of visual styles and demonstrated a reasonable understanding of physical motion and scene composition. Veo 1 was made available to a limited set of creators and filmmakers through a waitlist program, and was later integrated into YouTube Shorts as a generative tool. It did not include any audio generation capability.
In December 2024, Google released Veo 2, available initially through the VideoFX experimental platform. Veo 2 improved substantially on its predecessor with stronger physics modeling, more realistic motion trajectories, better camera control, and the ability to generate clips beyond two minutes in some configurations. The model supported up to 4K resolution output. Veo 2 also demonstrated improved understanding of cinematic framing conventions and was made available on Vertex AI for enterprise customers. It still generated video only, without audio.
Veo 3 was announced on May 20, 2025, at Google I/O. The central advance over Veo 2 was native audio-visual generation: rather than generating video and then applying audio as a post-processing step, Veo 3 generates both modalities simultaneously within a shared latent space. Google described this as the first time a video generation model had been trained to treat sound and image as jointly conditioned outputs from a single prompt. The model was made available the same day through Google AI Ultra subscriptions and via Vertex AI. Developer access through the Gemini API followed shortly after launch. The announcement drew immediate public attention, partly because of how quickly creators began sharing viral outputs, including realistic dialogue scenes, mock advertisements, and scenarios previously only achievable through conventional production.
The defining feature of Veo 3 is its ability to generate audio that is synchronized with video at generation time. Previous video generation models, including Veo 2, Sora, Kling, and Runway models, produced video-only output; any audio had to be added manually in post-production.
Veo 3 generates three categories of audio:
Veo 3 is built on a latent diffusion model transformer architecture. Both the video and audio streams are compressed into lower-dimensional latent representations before the diffusion process begins. The transformer then operates simultaneously across visual spacetime patches (height, width, and time) and temporal audio frames, allowing the model to learn statistical dependencies between audio events and corresponding visual events within a unified latent space.
The architecture uses cross-frame attention mechanisms to maintain object consistency across video frames, motion vector modeling to predict natural trajectories, temporal position embeddings, and a joint audio-visual decoder that reconstructs both streams from the shared latent representation at inference time. Because audio and video share the same latent space during training, synchronization is an intrinsic property of the model rather than a post-hoc alignment step.
The model was trained on large-scale datasets combining video, audio, and text metadata, enabling it to associate sonic properties with visual contexts: the sound of footsteps on different surfaces, the acoustic qualities of indoor versus outdoor spaces, and the relationship between a speaker's visible mouth position and the corresponding phonemes.
Google DeepMind's technical reports describe the training objective as maximizing the joint likelihood of the audio and video given a text or image conditioning input. This differs from prior approaches in which separate video and audio models were trained independently and then connected through an alignment module. The joint training approach means the model learns that a door slamming should produce a sharp transient sound at the exact frame the door contacts its frame, rather than learning this relationship through a secondary alignment step that is inherently imprecise. The tradeoff is increased training complexity and inference cost, since the model must maintain high-dimensional representations of both modalities throughout the generation process.
Veo 3 generates video at up to 1080p natively, with post-generation upscaling available to 4K in supported workflows. The model supports both 16:9 (landscape) and 9:16 (portrait/vertical) aspect ratios. Output runs at 24 frames per second, which is the standard for cinematic content. Audio is output at 48 kHz stereo.
Clip length at launch was limited to approximately four to eight seconds per generation. This is a practical constraint of the computational cost of joint audio-visual generation, as generating both streams simultaneously over longer durations increases inference time and memory requirements substantially.
Veo 3 accepts text prompts and, in supported configurations, image prompts (image-to-video). The model interprets descriptions of scenes, characters, actions, camera movements, lighting conditions, and audio cues within a single prompt. For example, a prompt can specify a camera movement, the style of dialogue a character should speak, the acoustic environment of the scene, and the mood of background music simultaneously.
Prompt adherence improved with the Veo 3.1 update in October 2025, which addressed cases where the model would deviate from explicitly described scene elements. The model handles cinematic vocabulary such as dolly shots, tracking shots, rack focus, and specific color grading references with reasonable fidelity.
Veo 3 supports image-to-video generation, where a static image is provided as the first frame and the model generates subsequent motion and audio. This feature is useful for animating still artwork, product photographs, or reference images. At launch, image-to-video was not available in the European Economic Area, Switzerland, or the United Kingdom due to regional restrictions.
Veo 3 provides camera control through natural language description. Users can specify camera movements such as zooms, pans, tilts, and tracking shots within the prompt. The Flow platform provides a more structured interface for camera control as part of its scene-building workflow. Supported camera descriptors include dolly in, dolly out, orbit, crane up, crane down, Dutch angle, and static lock. The model interprets these directions within the context of the scene geometry it generates, so a "tracking shot following a runner" will attempt to maintain the runner as the subject throughout the clip's duration.
Veo 3 accepts visual style guidance within prompts. Creators can reference specific film looks, such as film grain, aspect ratio, color grading style (warm desaturated, high contrast black and white, neon-lit), or a named cinematographer's aesthetic. The model does not reproduce copyrighted works, but will approximate visual properties associated with described styles. This capability is more reliable for broad aesthetic categories than for precise replication of specific works.
The original Veo 3 model, released May 20, 2025, generates up to eight seconds of video with synchronized audio from a text or image prompt. It is billed per second of generated video on Vertex AI ($0.50 per second for video only, $0.75 per second for video with audio) and is accessible to Google AI Ultra subscribers through Flow.
Veo 3 Fast is a lighter-weight variant of Veo 3 designed for faster generation and lower cost. It produces output at 720p rather than 1080p and generates video roughly twice as fast as the standard model. The quality tradeoff relative to the standard model is described by Google as small (approximately 1 to 8% degradation on internal quality benchmarks). Veo 3 Fast is suited for rapid prototyping, iterating on creative concepts, or high-volume generation workflows where cost is a priority. On the Gemini API, Veo 3 Fast is priced at $0.15 per second.
Veo 3.1 was released in October 2025 as an update to Veo 3. Google described it as focused on improved prompt adherence, scene comprehension, audio-visual alignment, and consistency across frames. Key additions in Veo 3.1 include:
Veo 3.1 also introduced a three-tier pricing structure: Veo 3.1 Light ($0.05 per video on the Gemini API), Veo 3.1 Fast ($0.15 per video), and Veo 3.1 Standard ($0.40 per video). A 4K resolution option (3840x2160) was added to Veo 3.1 Standard in a January 2026 update.
Veo 3.1 Fast generates video at approximately twice the speed of standard Veo 3.1 with a 1 to 8% quality reduction, making it practical for draft workflows. Veo 3.1 Light is the lowest-cost tier, outputting shorter clips at reduced resolution, suited for applications where generation volume matters more than output quality.
At launch in May 2025, Veo 3 was available exclusively to Google AI Ultra subscribers in the United States. Google AI Ultra costs $249.99 per month (with introductory pricing for new subscribers). The Ultra tier provides approximately 12,500 generation credits monthly, sufficient for roughly 625 Fast-tier videos or 125 Quality-tier videos in Flow.
Google AI Pro ($19.99 per month) received limited access to Veo 3 generation in Flow and the Gemini mobile app in subsequent months. Pro users receive approximately 1,000 credits per month, enough for roughly 10 high-quality Veo videos. Google later expanded Veo 3 access to more countries and to the Gemini mobile app as part of a broader international rollout covering over 71 countries.
Flow is a filmmaking-oriented platform launched by Google alongside Veo 3 at Google I/O 2025. It integrates Veo 3, the Imagen 4 image generation model, and Gemini's natural language capabilities into a single interface designed for cinematic production workflows. Flow provides a visual interface for building scenes, controlling camera movements, generating and extending clips, and managing prompt-driven production. The platform targets independent filmmakers, content creators, and advertising professionals who want to produce cinematic content without conventional production infrastructure.
Flow is the primary consumer interface for Veo 3 generation for Google AI subscribers. It includes a Scenebuilder tool that allows creators to chain multiple generated clips into a longer narrative sequence, with controls for maintaining visual consistency between scenes. The platform also supports text-to-video, frame-to-video, and camera control prompting from a single unified interface.
Vertex AI is Google Cloud's enterprise AI platform and provides API access to Veo 3 for developers and enterprise customers. Vertex AI access is billed per second of generated video. Enterprise customers generating significant video volumes can negotiate custom pricing. Vertex AI was one of the two platforms where Veo 3 was available on launch day, alongside the Google AI Ultra subscription tier.
The Gemini API provides developer access to Veo 3 through Google AI Studio. Veo 3 was made available via the Gemini API shortly after its launch at Google I/O. Developers can call the model programmatically to generate video and audio from prompts or reference images. The API is suitable for building applications that incorporate generated video content, media pipelines, or automated content creation workflows.
In 2025, Canva integrated Veo 3 into its platform through a "Create a Video Clip" feature, extending access to Canva's user base of designers and marketing professionals. The integration allows Canva users to generate short video clips directly within the Canva design environment without requiring a separate Google AI subscription.
| Platform | Model | Price |
|---|---|---|
| Vertex AI | Veo 3 (video only) | $0.50 per second |
| Vertex AI | Veo 3 (video + audio) | $0.75 per second |
| Vertex AI | Veo 3 Fast | $0.15 per second |
| Gemini API | Veo 3 Standard | $0.75 per second |
| Gemini API | Veo 3 Fast | $0.15 per second |
| Gemini API | Veo 3.1 Standard | $0.40 per video (8 sec) |
| Gemini API | Veo 3.1 Fast | $0.15 per video (8 sec) |
| Gemini API | Veo 3.1 Light | $0.05 per video (8 sec) |
| Google AI Ultra | Flow (via subscription) | $249.99/month (includes credits) |
| Google AI Pro | Flow (via subscription) | $19.99/month (limited credits) |
All prices are as of mid-2025. Vertex AI and Gemini API pricing is subject to change and enterprise volume discounts may apply. The per-second billing model on Vertex AI means costs scale predictably with output duration: an eight-second clip with audio costs $6.00 at standard rates, while the same clip at Veo 3.1 Standard via the Gemini API costs $0.40.
At the time of Veo 3's launch, the major competing commercial video generation models were Sora 2 from OpenAI, Kling 2.0 from Kuaishou, and Runway Gen-4 from Runway. Veo 3 was the only model in this group to offer native audio generation as a core output.
| Model | Developer | Native audio | Max resolution | Max clip length | Approx. API cost |
|---|---|---|---|---|---|
| Veo 3 | Google DeepMind | Yes (dialogue, SFX, music) | 1080p (4K via upscale) | 8 sec | $0.75/sec (with audio) |
| Veo 3.1 | Google DeepMind | Yes | 1080p / 4K | 8 sec | $0.40/video |
| Sora 2 | OpenAI | No | 1080p | 20 sec | ~$0.15/sec |
| Kling 2.0 | Kuaishou | No | 1080p | 10 sec | ~$0.10/sec |
| Runway Gen-4 | Runway | No (add separately) | 1080p | 10 sec | ~$0.15/sec |
| Wan 2.1 | Alibaba | No | 720p | 5 sec | Lower cost |
Veo 3's primary differentiation from competitors is the synchronized audio output. In independent evaluations conducted shortly after launch, Veo 3 consistently placed first or near the top for lip-sync accuracy, dialogue generation, and ambient sound realism. In pure visual quality metrics, Runway Gen-4 and Sora 2 were considered competitive peers, with some benchmarks placing Runway Gen-4 slightly ahead on frame-level visual fidelity following its late 2025 "World Engine" architecture update. For high-volume or cost-sensitive workflows, Kling and Wan offered lower per-second costs at the expense of visual quality and no audio capability.
Veo 3 has a higher price point per second of video than most competitors, reflecting the additional computational cost of joint audio-visual generation. Veo 3 Fast partially closes this gap at $0.15 per second, which is in line with Sora 2 and Runway Gen-4 pricing.
Sora ceased to be available as a standalone product in April 2026, which changed the competitive landscape for video generation. As of mid-2026, the main alternatives to Veo 3.1 are Runway Gen-4.5, Kling 3.0, and Luma Dream Machine, none of which include native audio generation.
Veo 3 and Flow together provide independent filmmakers with a path to producing short-form content with production values that previously required camera equipment, sets, actors, and post-production facilities. Filmmakers use Veo 3 to generate establishing shots, b-roll footage, scene extensions, and test renders for visual concepts before committing to full production. The native dialogue capability means that character scenes can be roughed out from prompts rather than requiring voice actors and lip-sync work.
Marketing teams use Veo 3 to generate concept videos, product demonstration clips, and social media content. The ability to generate video with synchronized voiceover or character dialogue reduces the production cost of short-form advertising content. Agencies use the model to test multiple creative directions quickly before committing production resources to a final version. Direct-to-consumer brands have used Veo 3 to generate product unboxing-style videos, spokesperson clips, and testimonial-format content at a fraction of the cost of hiring actors and production crews. The short clip length of eight seconds aligns well with the format requirements of many paid social advertising placements, where shorter clips often outperform longer ones in engagement metrics.
Creators on platforms such as YouTube, TikTok, and Instagram use Veo 3 to generate short clips with audio for posting directly as content or as components of larger edited videos. The 9:16 vertical output format supported by Veo 3.1 is suited to mobile-first platforms. Clips of characters delivering short monologues, mock product reviews, and fictional news segments became common Veo 3 output formats in the months following launch.
Production teams use Veo 3 Fast to generate animated storyboards and rough cuts before entering full production. The lower cost and faster generation speed of the Fast variant makes iterative ideation more practical. Directors can visualize lighting, camera angles, and action sequences without on-set production.
Educators and corporate training developers use Veo 3 to produce explainer videos, historical recreations, and scenario-based training content. The ability to generate a character explaining a concept with synchronized dialogue reduces reliance on human talent for short educational clips. Training departments at companies have used Veo 3 to generate compliance training videos and product onboarding content without commissioning full productions.
All videos generated by Veo 3 carry a SynthID watermark embedded by Google DeepMind. SynthID is a steganographic watermarking system that encodes a signal imperceptible to human viewers into the generated content. The watermark is designed to persist through common transformations such as resizing, compression, and format conversion.
Google also announced plans to add a visible "Made with AI" overlay to Veo 3 outputs as access expanded beyond the initial Ultra subscriber base, providing a visible indicator for viewers encountering the content on social media or other platforms. This visible watermark appeared in the bottom corner of videos generated through Flow for most users.
SynthID detection requires access to Google's SynthID Detector tool, which is not publicly available to end users. This means a typical viewer cannot independently verify whether a given video was generated by Veo 3. Google acknowledged this limitation and noted that the Detector tool was not widely deployed at the time of Veo 3's launch.
SynthID only detects content generated by Google AI systems. Videos generated by Sora 2, Runway, Kling, or other non-Google systems are outside its scope. Academic research has also demonstrated that adversarial methods can degrade SynthID watermark detectability, with one published approach ("UnMarker") achieving a 79% bypass rate against the system.
Veo 3 drew significant immediate attention after its May 2025 launch. The key novelty of synchronized audio generation produced viral social media moments, as creators shared clips that demonstrated realistic dialogue, ambient sound, and music generated from text prompts. Examples circulated widely included scenes of characters engaged in realistic conversations, mock documentary segments, and fictional news broadcasts. One of the most widely shared early examples was a clip of the Loch Ness Monster playing bagpipes, which circulated across social media platforms within days of launch and was cited by multiple journalists as demonstration of the model's ability to create entertaining, physically plausible content with matching audio.
Technology press coverage was generally positive about the technical advance. CNBC described Veo 3 as representing a meaningful jump from prior video generation tools due to the audio integration. The Verge and TechCrunch covered its launch as one of the more significant announcements from Google I/O 2025, alongside Gemini 2.5 and Imagen 4. DataCamp noted that Veo 3 represented a qualitative shift in what was expected of video generation systems, as the inclusion of native audio meant that generated clips could be published without additional post-production work for many use cases.
Creators who gained early access through Google AI Ultra reported that the model produced outputs substantially more convincing than Veo 2, particularly for any scene involving character speech. The lip-sync quality was widely noted as a departure from the uncanny valley quality of prior AI video dialogue.
Some commercial users reported that audio synchronization worked well on approximately 25% of generations on the first attempt, with multiple regenerations often required to achieve the desired audio-visual alignment. This was one of the issues Veo 3.1 addressed in its October 2025 update.
Media organizations and researchers raised concerns about the misinformation potential of the model's realism. TIME Magazine reported that it was able to generate realistic-looking fabricated videos, including scenes depicting civil unrest, ballot destruction, and fabricated news scenarios, using Veo 3. Experts interviewed for that reporting noted that while the videos contained detectable flaws on close inspection, they were realistic enough to be plausible when viewed quickly in a social media context. The combination of visual realism with synchronized dialogue and ambient audio, absent from prior generation tools, made Veo 3 outputs harder to identify as AI-generated than its predecessors.
Veo 3 has several documented technical limitations:
Clip length: Generation is limited to eight seconds per clip at launch. Longer-form content requires stitching multiple clips together or using the scene extension capability introduced in Veo 3.1. This is a practical constraint of the computational cost of joint audio-visual diffusion.
Audio synchronization reliability: Audio synchronization quality varies across generations. Complex scenes with multiple speakers, rapid movement, or overlapping sounds are more likely to produce misaligned audio. Users often need multiple generations to achieve a clip where both the visual content and audio match the prompt as intended.
Hand and finger generation: Human hands remain a persistent weak point for Veo 3, consistent with limitations seen in other video and image generation models. Fingers frequently appear in anatomically incorrect configurations, particularly during rapid motion or when the hand is partially occluded.
Physics accuracy: While Veo 3 handles common physical scenarios with reasonable fidelity, complex fluid dynamics, cloth simulation, and intricate mechanical interactions produce inconsistent results. The model sometimes prioritizes visual plausibility over physical accuracy in ambiguous cases.
Hallucinations: The model occasionally generates visual content not specified in the prompt, or loses consistency in object appearance across frames. Characters may change subtly in appearance between shots, and objects can morph or disappear in longer clips.
Regional restrictions: Image-to-video was not available at launch in the European Economic Area, Switzerland, or the United Kingdom.
Access cost: The $249.99 monthly cost of Google AI Ultra placed Veo 3 out of reach for many independent creators at launch. The Veo 3 Fast API tier at $0.15 per second and the Veo 3.1 Light tier at $0.05 per video provided more affordable options as the ecosystem matured.
Misinformation risk: The realism of Veo 3's audio-visual output, particularly the native dialogue generation with lip-sync, creates a meaningful capability for generating fabricated video content that is harder to detect as AI-generated than outputs from prior tools. This has been documented by media researchers and is an ongoing concern for platform trust and information integrity.