Veo 3.1 · ネイティブ音声付きの映画品質 AI 動画
Google DeepMind の旗艦動画モデルが OVOV に登場。プロンプトや画像から、映像とセリフ・環境音・効果音が同時生成される 8 秒の映画品質クリップを作成。
See Veo 3.1 in action
Real cinematic outputs with native audio — click the speaker to hear Veo's synchronized sound.
Hover to play · Click speaker to unmute
See Veo 3.1 in action
Real cinematic outputs with native audio — click the speaker to hear Veo's synchronized sound.
異星のファンタジー世界
ラグジュアリー香水広告
製品発表会ティザー
モルディブ旅行 CM
東洋武侠の頂上決戦
ハリウッド風レース映画
宇宙船が深い星空へ
ゴールデンレトリバーと蝶
寿司職人の手仕事
赤いドレスの女性が崖に立つ
深夜の達人対決
ハンディセルフィー Vlog
ジューシーグルメクローズアップ
ストリートダンス高速アクション
ラグジュアリー口紅広告
Why Veo 3.1 leads the field
Google DeepMind's most advanced video model — the one that made native audio and true cinematic control standard.
Native Synced Audio
Veo 3.1 generates the soundtrack together with the picture — dialogue, ambient sound, and effects locked to the action. No separate audio pass, no lip-sync drift.
Cinematic Camera Control
Understands directorial language — dolly, pan, crane, rack focus. Describe the shot the way a cinematographer would and Veo 3.1 renders it.
First & Last Frame
Give Veo a start frame, or a start and end frame, and it animates the motion between them — ideal for product reveals and controlled transitions.
Up to 4K Output
Render at 720p, 1080p, or true 4K. Native 16:9 widescreen and 9:16 vertical for social, all at 8 seconds.
Reference-Guided Generation
Feed up to 3 reference images to lock character, style, or composition across the clip on the Fast tier.
Two Official Tiers
Veo 3.1 Fast for quick iteration, Veo 3.1 Quality for final delivery — both official Google DeepMind channels, both with native audio.
From prompt to cinematic clip in under 2 minutes
Veo 3.1 works like a film crew that never sleeps — describe the scene, it shoots and scores it.
Describe your shot
Write the scene, the camera movement, and the sound you want. Add a reference image for image-to-video. Veo understands natural cinematic language.
Veo 3.1 shoots and scores
The model generates 8 seconds of video with synchronized native audio in a single pass — dialogue, ambience, and effects included.
Download and use
Get your clip in up to 4K with full commercial rights and no watermark. Ready for ads, social, or film.
What you can create with Veo 3.1
Veo 3.1's native audio and cinematic control shine wherever a clip needs to feel produced, not generated.
Product & Brand Films
8-second hero clips with dramatic reveals and synced sound design.
- Golden-hour product reveals with ambient audio
- Dialogue-driven brand spots
- Cinematic B-roll for landing pages
Social & Short-Form
9:16 vertical clips built for Reels, Shorts, and TikTok.
- Scroll-stopping vertical hooks
- Native sound that survives autoplay
- Trend-ready 8-second loops
Storyboards & Pre-viz
Turn a still frame into motion to preview a scene before you shoot.
- First-and-last-frame transitions
- Reference-locked character motion
- Concept clips for pitches
Ad Creative Testing
Spin up multiple audio-synced variants to test which hook converts.
- Rapid variant generation on the Fast tier
- Sound-on ad concepts
- Cinematic quality without a crew
Prompt writing guide for Veo 3.1
Veo 3.1 rewards specific, cinematic direction — and it can generate audio, so describe sound too.
Direct the picture and the sound in the same prompt
Lead with subject and action
Open with who or what is on screen and what they do. Veo 3.1 anchors the whole clip on a clear main subject.
- •Name the subject in the first few words
- •Give one clear action per clip
- •Keep it to a single continuous moment — you have 8 seconds
Example
"A weathered fisherman hauls a net over the side of a small boat at dawn."
Direct the camera
Veo understands real cinematography terms. Specify the move and the framing to control the feel.
- •Use terms like dolly in, slow pan, crane up, rack focus
- •State the shot size: wide, medium, close-up
- •One camera move per clip reads cleaner
Example
"Slow dolly-in on the fisherman's face, shallow depth of field, golden backlight."
Describe the sound
This is Veo's superpower — it generates synchronized native audio. Spell out dialogue, ambience, and effects.
- •Put spoken lines in quotes for dialogue
- •Name ambient sound: waves, wind, distant gulls
- •Mention key sound effects tied to the action
Example
"Ambient: gentle waves and creaking rope. He mutters, "Almost there.""
Set lighting and mood
Light defines the emotion. Veo 3.1 renders time of day, weather, and color grade faithfully.
- •Name the time of day and light source
- •Add a mood word: serene, tense, nostalgic
- •Reference a look: cinematic, documentary, film noir
Example
"Golden hour, warm rim light, soft haze — serene and cinematic."
Lock a visual style
Pin the aesthetic so the clip matches your brand or reference. Fast tier also accepts up to 3 reference images.
- •Name a genre or era for consistency
- •Add lens hints: 35mm, anamorphic, macro
- •On the Fast tier, attach reference images for character or style
Example
"Shot on 35mm film, muted teal-and-amber grade, subtle grain."
Choreograph the motion
Because clips are 8 seconds, plan one clean arc of motion rather than many events.
- •Describe how the subject or camera moves through the shot
- •Avoid cramming multiple scene changes into one clip
- •For transitions, use first-and-last-frame image-to-video instead
Example
"The boat drifts left to right across frame as the sun climbs, a single unbroken take."