Listing video with an AI avatar: HeyGen for Real Estate, and Sume
HeyGen launched a real estate offer for listing videos. With Sume you can build one from an avatar, a property photo as the scene and a 4-60 second script.
With Sume, a listing video is an avatar talking video whose scene is a photo of the property (scene: { "type": "photo", "image_url": "..." }) and whose script runs 4-60 seconds. Sume's docs describe an API, not a managed real estate service; HeyGen's August 2026 notes describe a real estate offer that includes a done-for-you option.
What did HeyGen launch?
HeyGen's August 2026 notes describe "Listing videos for every property" and a service option: "Text us what you want, we produce the video, and you approve before it publishes". Those are HeyGen's own descriptions.
How do I build a listing video with Sume?
Create an avatar for the presenter, then send the script and the property photo. Media fields must be fetchable public HTTPS URLs. Leave out product_image if there is no product; the docs say an avatar video without one is fine.
curl -X POST https://api.sume.com/v1/avatar-1.0/talking-video \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: listing-001" \
-d '{
"avatar_handle": "agent_presenter",
"script": "Welcome to 12 Example Street. Three bedrooms, a sunny kitchen and a quiet garden. Book a viewing today.",
"scene": { "type": "photo", "image_url": "https://example.com/listing-front.jpg" },
"aspect_ratio": "9:16"
}'How do I approve before I pay for the render?
Create an avatar video preview first. It returns first-frame stills, and you call generate-video on the preview id only when the framing looks right. That gives you an approval step before the full render.
| Need | HeyGen (per its notes) | Sume |
|---|---|---|
| Property scene | Listing video formats | scene photo image_url |
| Approval | Approve before it publishes | Preview, then generate-video |
| Length | Not stated in the notes | 4-60 s per video |
What should I check first?
Only use photos you have rights to, and follow your local listing rules for AI-generated presenters. The docs cover the API fields; they do not cover real estate advertising law.
Sources
Related posts
More in Use cases
- Hinglish text to speech API: romanized Hindi with language hi
For romanized Hindi or Hinglish on Sume TTS, send language `hi` even though the text is Latin script, and pin a Sonic model id on the Router.
- Holiday ad creative by phase: four videos, one bulk run
Meta splits the holidays into discovery, deals, gifting and fresh start. Queue one video per phase as a single Sume bulk run with a spend cap on each.
- India's synthetic-media label rule: does routine editing count?
India's amended IT rules exclude routine editing, formatting and compression from synthetic media, and require a prominent label on the rest. What Sume offers.
- Instagram API: JPEG only, no MPO or JPS. Stills from a video frame
Meta's publishing guide says JPEG is the only image format and MPO and JPS are not supported. Sume video-frames returns jpeg by default, or png.
Written by Sume