Real estate agent intro clip: headshot, logo and listing photos
Send a headshot, your logo and listing photos as reference_image_urls to Gemini Omni Flash 1.1 and address each as <IMAGE_REF_n> for a 3 to 10 second intro.

For a branded real estate intro, put the agent's headshot, the brokerage logo and two or three listing photos into reference_image_urls on gemini-omni-flash-1.1, and refer to each as <IMAGE_REF_0>, <IMAGE_REF_1> and so on in the prompt. The index follows your list order, starting at 0. You get a 3 to 10 second clip with native audio.
Do not rely on the model to draw a logo or an address. Overlay the real logo and address afterward. Source: Video Router, read 2026-10-04.
Reference order
Order the references so the prompt reads naturally. The tag numbers below are the ones to use in the example.
| Index | Image | Used for |
|---|---|---|
| <IMAGE_REF_0> | Agent headshot | The presenter's likeness |
| <IMAGE_REF_1> | Front of the house | The establishing setting |
| <IMAGE_REF_2> | Living room | The interior the camera moves into |
| <IMAGE_REF_3> | Logo on a plain background | Palette and mood only |
Request
Use the headshot only with the agent's consent, and keep the property photos honest. A generated move through a room is an interpretation, so avoid prompts that add features the house does not have.
curl -X POST https://api.sume.com/v1/video-router/generate \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: listing-intro-001" \
-d '{
"model": "gemini-omni-flash-1.1",
"prompt": "The agent from <IMAGE_REF_0> stands in front of the house in <IMAGE_REF_1>, smiles, gestures toward the door, and the camera follows inside to the room in <IMAGE_REF_2>. Warm morning light. Colors echo <IMAGE_REF_3>. Soft room tone only.",
"reference_image_urls": [
"https://example.com/agent.jpg",
"https://example.com/front.jpg",
"https://example.com/living-room.jpg",
"https://example.com/logo.png"
],
"resolution": "1080p",
"aspect_ratio": "9:16",
"duration": 8,
"mode": "async"
}\Add the real details
Add the address, price and phone number with Timeline compose in overlay mode: a still plate over your clip at a position you choose, a flat $0.02 per job. For spoken-word captions, POST /v1/video-captions is $0.20 for a clip up to 60 seconds, and a clip with no speech needs cues.
References are guidance, not frames
Plain image_to_video is the better route when you want the actual photo as the first frame. Reference-to-video treats images as guidance and does not promise to reproduce them exactly.
Sources
Related posts
More in Use cases
- Listing clip from photos with Seedance 2.5, and what to disclose
Nine listing photos can feed a Seedance 2.5 reference-to-video request on Sume. Price a 30 s clip, plan the camera path, label it AI-generated.
- Real estate price-reduction clip from one listing photo: $0.83 each
A 5-second vertical price-drop clip from the hero photo with the new price burned in as cues: $0.825 per listing, $9.90 for 12, on Sume from docs.
- Rehearsal dinner slideshow: 24 photos and Timeline's 8-fade cap
A 24-photo slideshow with fades fails if every cut is a fade: Timeline refuses more than 8 chained transitions. Insert hard cuts; 96 seconds costs $0.20.
- 40 fixed phone prompts in one TTS job: no streaming needed
Fixed prompts do not need 150 ms streaming. Render them once as sentence slices with Sume TTS and play files. Worked cost for 40 prompts of 60 characters.
Written by Sume