Codex Voice Mode With GPT-6 Astra: What the Blender Demo Leaves Out
By Matt Cullerton, founder of Mavric and Apso
A sponsored TikTok from Chase AI (@chase_ai_) shows a website with a 3D Blender hero built entirely through ChatGPT's voice mode driving Codex. The voice layer, the image skill and the auto-approval mode are real OpenAI features. The Blender connection is not something OpenAI ships, and the finished site in the video runs on localhost, so the "I deployed it" claim has no visual support.
What does the demo show?
He speaks a prompt into ChatGPT's voice surface: "Use your image-generation skill and create six mockups for a hero section that we are going to turn into a 3D asset using Blender." The result is a gallery titled "Six living hero directions," a Blender scene labeled Magnetic infinity / 1792 tiles, and a dark site branded APERTURE with an interactive sculpture you can scatter, expand and reassemble.
He says: "So I had Codex use Blender for me. I've never used Blender before, but it handled everything," and closes with "if you haven't tried out Astra yet, now is the time."
What is GPT-6 Astra?
The model chip on screen reads GPT-6 Astra High early on and GPT-6 Astra Ultra later. OpenAI's models page lists GPT-6 Astra as "Our most capable model for complex work across code, apps, and research." Wikipedia dates its limited preview to September 3, 2026 and general availability to September 4, 2026. CNBC covered the rollout.
What are the GPT-6 effort levels?
The models page lists Light, Medium, High, Extra High, Max and Ultra. It says "Ultra mode goes beyond a single-agent run. It uses subagents to accelerate complex work." It also states that "GPT-6 Luna supports reasoning efforts up to Max, but not Ultra." It does not explicitly confirm Ultra for Astra, so the on-screen chip is the evidence that the pairing works.
Does Codex have an image generation skill?
Yes, as a sample. OpenAI's skills documentation defines Agent Skills as packages that "package instructions, resources, and optional scripts so either product can follow a workflow reliably," and lists two bundled system skills, Skill Creator and Skill Installer.
The openai/codex repository also includes a sample skill called imagegen. Its description reads: "Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts."
Skills run two ways: explicitly, by typing @ in ChatGPT or $ in Codex, or implicitly, when the model matches the task to a skill description. Saying "use your image-generation skill" out loud relies on the implicit path.
Can ChatGPT Voice control Codex?
Partly. OpenAI's Voice docs say it supports "natural turn-taking," runs on the GPT-Live model, and is available on Plus, Pro, Business, Edu and Enterprise. They say Voice can "start a Codex task" and "check active tasks." That is narrower than building, refining and deploying a site entirely by voice.
What does "Approve for me" do?
It is the setting that makes a long unattended run possible, and the video never mentions it. OpenAI's auto-review page describes it as a mode that swaps human approval for a separate reviewer agent at the sandbox boundary, with the same network and filesystem limits. The page calls it "a reviewer swap, not a permission grant." Selecting an approved model switches the control to Approve for me when your account and organization policy allow it.
How did Codex connect to Blender?
The video does not say. OpenAI publishes no Blender integration, and the Codex-to-Blender options that exist are community MCP servers and third-party agent skills. The clip cuts from the voice prompt to a finished 1,792-tile scene.
The scene's details suggest code built it. Objects are named Tile_000_00 upward in a two-index pattern that a script produces, and the timeline sits at Blender's default range of frame 1 to 250. Which tool or script did it is not shown, so a viewer trying to reproduce the demo has to find their own bridge.
Was the site actually deployed?
Not in anything the video shows. He says "I refined it. I deployed it," but every shot of the finished site shows the address bar at 127.0.0.1:4175, a local development server. No frame shows a public URL, build log or hosting dashboard. The refinement is visible, as the sculpture changes across frames.
Is this a sponsored post?
Yes. The caption is @ChatGPT #ChatGPT_Partner, a paid-partnership disclosure. Android Headlines reports that HypeAuditor counted sponsored Instagram posts with that tag rising from 61 in June to 122 in July to 141 in August 2026, and that OpenAI hired Charles Porch, formerly Instagram's head of partnerships, and engaged the agency Viral Nation to run creator campaigns. The terms of this partnership are not public.
Bottom line
ChatGPT Voice can start Codex tasks, the imagegen sample skill makes mockups, and Approve for me lets an agent run without stopping for permission. To repeat this demo you also need a Blender bridge OpenAI does not provide, and you still have to deploy the site yourself.
Sources
- GPT-6 Astra on Wikipedia - release dates
- Models, ChatGPT Learn - Astra description and effort tiers
- Build skills, ChatGPT Learn - Agent Skills and invocation
- imagegen SKILL.md, openai/codex - the sample image skill
- ChatGPT Voice, ChatGPT Learn - voice features and Codex tasks
- Auto-review, ChatGPT Learn - Approve for me
- Android Headlines on OpenAI's creator campaign - sponsorship context
- CNBC on the GPT-6 Astra rollout - rollout coverage
Published September 25, 2026. Based on a TikTok by @chase_ai_. Full video notes (markdown)