Dialogue scene
“They talk naturally; one says "So I finally booked the tickets," the other laughs and replies "No way — when do we leave?"”
Google · video model
Veo 3.1 Native DialogueGenerate spoken-dialogue video
4 credits / second · every plan · price breakdown · API playground
Animate a photo
Upload a start frame, then script the dialogue, performance, and sound.
Made with Veo 3.1 Native Dialogue · Dialogue scene
Veo 3.1 Native Dialogue animates a start image into an 8-second talking scene where the dialogue, lip movement, vocal performance, and environmental sound are all generated together — script the lines in quotes and the model performs them.
Original results
Veo 3.1 Native Dialogue examples made in Made
These examples use media produced for Made. Prompts are included when the production record allows them.
Street interview
“The reporter asks "What sells out first every morning?" and the vendor grins: "The peonies. Always the peonies."”
Kitchen banter
“One cook says "Table twelve is yours," the other answers "On it — behind!" as pans clatter around them”
Start-frame control
“Use this image as the opening composition.”
Scene brief
“Cast the scene as a still, then script the dialogue on top of it.”
Composition brief
“Plan the framing as a still, then hand the performance to the model.”
Where Veo 3.1 Native Dialogue fits best
Best uses
- Lip-synced spoken dialogue generated natively with the picture
- Two-person conversations and back-and-forth banter
- Street-interview and UGC-style talking clips from a single still
- Vocal performance plus ambient sound in one pass — no dubbing step
Limits to know
- Every generation requires a start image — there is no text-to-video mode; create the frame first with an image model.
- Format is fixed: 8 seconds, 9:16, 720p — no duration, aspect, or resolution controls in Made.
- Premium per-second pricing (currently an estimated provider rate) — draft the frame and script before committing.
Specifications in Made
These are the controls exposed by Made, which may be narrower than a provider’s full API.
- Aspect ratios
- 9:16 (fixed)
- Resolution
- 720p (fixed)
- Duration
- 8 seconds (fixed)
- Output formats
- MP4 with audio
- Reference images
- 1
- Processing
- Fixed-length renders; progress appears in the generation view.
How to use Veo 3.1 Native Dialogue in Made
- 1
Create the start frame
Every generation animates a still — generate one with an image model or upload a photo with the speakers framed the way you want.
- 2
Script the dialogue
Put spoken lines in quotes and note who says what; the model performs them with matching lip movement and vocal delivery.
- 3
Direct the performance and sound
Describe tone, pacing, gestures, and the environmental sound around the speakers — it is all generated together.
- 4
Review and refine
Check lip-sync, delivery, and ambience, then adjust the script or direction one line at a time.
Compare relevant models
video
Veo 3.1
Veo 3.1 is Google’s flagship video model, generating 4 or 8 second clips with natively synchronized audio from a text prompt, with optional start and end frames to pin the first and last shot.
Explore model →video
Veo 3.1 Lite
Veo 3.1 Lite is the cost-efficient tier of Google’s Veo 3.1 family, generating 4, 6, or 8 second clips at 720p with natively synchronized audio from a text prompt or a start image.
Explore model →video
Happy Horse 1.1
Happy Horse 1.1 is Alibaba’s flagship video model — a long-running #1 on the Artificial Analysis Video Arena — generating 3 to 15 second clips at 1080p with native audio and multilingual lip-sync.
Explore model →Continue with a related tool
AI Video Generator
Turn any image into a captivating video. Upload a photo, describe the motion you want, and watch AI bring it to life with realistic movement, cinematic camera work, and professional quality.
See the tool →AI Image Generator
Create scroll-stopping product photos and marketing visuals in seconds. Describe your shot, pick your style, and get professional images ready for your store, social feed, or ad campaign.
See the tool →It is Made’s dialogue-tuned route into Google’s Veo 3.1 image-to-video endpoint: the speech, lip movement, vocal performance, and environmental sound are created together with the picture rather than dubbed on afterward.