David Roberts Turned a Zillow Listing Into a Cinematic Property Ad Using Only AI
A luxury real estate video built entirely from Zillow photos using AI image animation, voiceover, and music in under 15 minutes.
The Strategy
David Roberts runs Calico AI and demonstrates how to take a standard Zillow listing with no video and turn it into a polished luxury property ad using a chain of AI tools. The listing is a $5 million home in Old Enfield, Austin with no video content attached, which he frames as a gap that agents and marketers can fill to boost listing visibility and clicks. The workflow starts by pulling six high quality images directly from the Zillow listing page and feeding them through VEO 3.1 inside Calico AI to generate cinematic video clips. Each image gets a custom motion prompt generated by a purpose built GPT that analyzes the photo and suggests camera movements like slow dolly pans and stabilized micro zooms suited to luxury real estate aesthetics. For the audio layer, a second custom GPT ingests the Zillow listing URL and writes a 30 second voiceover script covering the property highlights, square footage, location, and key selling features. That script goes into ElevenLabs to generate a professional AI voice narration. A background music track is also generated in ElevenLabs with a prompt for peaceful, luxury inspired scoring. Everything gets assembled in CapCut where the video clips are laid on the timeline, the AI voiceover is synced, the music is layered underneath, and auto generated captions are added. The final output is a complete listing video ready to upload to Zillow, YouTube, or social media. David notes that Calico AI is building a canvas workflow feature that will automate this entire process into a single trigger, eliminating the need to switch between tools manually.
How It Works
Open the Zillow listing and select six of the strongest images. Download each image to your computer. Prioritize exterior shots, kitchen, living spaces, pool, and any unique architectural features.
In Calico AI, go to Videos and select the VEO 3.1 model. Set the aspect ratio to 16x
Upload the first image as a reference image. Adjust the aspect ratio if the image dimensions do not match VEO 3.1 requirements.
Use the Luxury Architect Image to Video Prompt Generator custom GPT. Drop in the image and copy the generated motion prompt describing camera movement, focal anchors, and pacing.
Paste the motion prompt into Calico AI and generate the video clip. Repeat this process for all six images.
Download all generated video clips from the Calico AI project folder.
Copy the Zillow listing URL and paste it into the Listing Video Voice Over Writer custom GPT. This generates a 30 second voiceover script covering property details, selling features, and location highlights.
Paste the generated voiceover script into ElevenLabs. Select a voice and generate the speech audio. Download the file.
In ElevenLabs, generate a 30 second background music track with a prompt for luxury real estate, peaceful and serene. Download the music file.
Open CapCut and import all video clips to the timeline. Mute the video track audio. Import the ElevenLabs voiceover and place it on the audio timeline. Import the music track and layer it underneath.
Use CapCut auto captions to generate subtitles on the bottom of the video. Review the final output for timing and export.
Results
No business revenue or conversion results are provided. The video demonstrates the workflow on a $5 million Austin listing with 2,375 views at time of review. David mentions that his team offers done for you listing video creation as a service but does not share pricing or client outcomes.
Our Take
This is a clean, replicable creative workflow for real estate agents who want listing videos without hiring a videographer. The custom GPT for motion prompts is the smartest piece because it solves the hardest part of AI video generation: knowing what to prompt. The quality of the VEO 3.1 output shown in the demo is genuinely impressive for still photo animation. The main limitation is that this is still a manual multi tool process today. David acknowledges this and says Calico AI is building automation to handle it in one step, but that is not yet available. There are also no verified results showing whether these AI listing videos actually increase clicks or sell homes faster. Best suited for real estate agents, property marketers, or agency builders who want to offer listing video creation as a service at scale once the automation ships.
Related Strategies
More AI agent strategies you might find useful
Fully Autonomous Meta Ads Manager Built on OpenClaw
Matthew Berman runs his entire Meta ads operation autonomously with OpenClaw for…
How Lauren Lucas Grew Her Real Estate Business to $400K GCI Using AI Automation
Lauren Lucas grew to $400K GCI by building AI systems that run her real estate b…
How Barrett Linburg Gave Claude Full Context on a 50-Property Real Estate Operation Before Typing a Word
Barrett Linburg built an Obsidian knowledge base connected to Claude Code so Cla…
Want more strategies like this?
Get weekly AI agent case studies in your inbox.