---
title: "Codex Voice Mode With GPT-6 Astra: What the Blender Demo Leaves Out"
date: "2026-09-25"
video_id: "7689599987612749070"
tiktok_url: "https://www.tiktok.com/@chase_ai_/video/7689599987612749070"
creator: "@chase_ai_"
category: "AI"
tags: ["codex", "gpt-6 astra", "chatgpt voice", "agent skills", "blender"]
excerpt: "A sponsored Codex voice demo runs GPT-6 Astra at Ultra effort with Approve for me on. What OpenAI ships, what the Blender step needs, and why it was localhost."
---
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](https://learn.chatgpt.com/docs/models) lists GPT-6 Astra as "Our most capable model for complex work across code, apps, and research." [Wikipedia](https://en.wikipedia.org/wiki/GPT-6_Astra) dates its limited preview to September 3, 2026 and general availability to September 4, 2026. [CNBC](https://www.cnbc.com/2026/09/03/open-ai-astra-gpt-6-cyber.html) 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](https://learn.chatgpt.com/docs/build-skills) 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`](https://github.com/openai/codex/blob/main/codex-rs/skills/src/assets/samples/imagegen/SKILL.md). 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](https://learn.chatgpt.com/docs/features/voice) 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](https://learn.chatgpt.com/docs/sandboxing/auto-review) 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](https://www.androidheadlines.com/2026/09/openai-hires-influencers-for-chatgpt-everyday-use.html) 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](https://en.wikipedia.org/wiki/GPT-6_Astra) - release dates
- [Models, ChatGPT Learn](https://learn.chatgpt.com/docs/models) - Astra description and effort tiers
- [Build skills, ChatGPT Learn](https://learn.chatgpt.com/docs/build-skills) - Agent Skills and invocation
- [imagegen SKILL.md, openai/codex](https://github.com/openai/codex/blob/main/codex-rs/skills/src/assets/samples/imagegen/SKILL.md) - the sample image skill
- [ChatGPT Voice, ChatGPT Learn](https://learn.chatgpt.com/docs/features/voice) - voice features and Codex tasks
- [Auto-review, ChatGPT Learn](https://learn.chatgpt.com/docs/sandboxing/auto-review) - Approve for me
- [Android Headlines on OpenAI's creator campaign](https://www.androidheadlines.com/2026/09/openai-hires-influencers-for-chatgpt-everyday-use.html) - sponsorship context
- [CNBC on the GPT-6 Astra rollout](https://www.cnbc.com/2026/09/03/open-ai-astra-gpt-6-cyber.html) - rollout coverage


## Video description and verification notes

**A 54-second 1080x1920 clip uploaded 2026-09-25 by @chase_ai_ (channel "Chase AI"), captured at 2,344 views, 91 likes, 1 comment, 16 reposts, and 63 saves. The caption is two tokens long: `@ChatGPT  #ChatGPT_Partner`. The 183-word Whisper transcript splits into 17 cues. Across 27 frames sampled at 2-second intervals there are zero burned-in captions, so every string on screen is application UI. The inventory: a dark site branded `APERTURE` with nav items `The idea`, `Inside APERTURE`, `Explore the demo`, hero copy `A place for every possibility.` and `Connect the ideas you already have.`, a yellow `Explore the demo ↗` button, a hint label `Disturb the surface`, and a footer strip reading `A STUDY IN CONNECTION` with `Brush to scatter · Click to expand · Drag to rotate`, later `Click to reassemble · Drag to explore`, later `Scroll to reconnect · Drag to explore`, alongside controls `Expand sculpture ↗`, `Reassemble ↗`, `Reset`, and `Pause motion`; a mockup gallery headed `Six living hero directions.` with the note `Charcoal + acid yellow. Click any mockup to inspect the full image. These are image-generated visual concepts.` and six entries `01 / Robotic face` ("Intelligence, looking back."), `02 / Precision robot arm` ("From intent to action."), `03 / Mechanical iris` ("Focus on what matters."), `04 / Magnetic sculpture` ("Order, out of possibility."), plus two partly cropped tiles reading `Give your ideas shape.` and `A little more capable`; a full-screen voice surface with a blue orb, a composer placeholder `Do anything`, a permissions control `Approve for me`, a model chip reading `GPT-6 Astra High` and later `GPT-6 Astra Ultra` with `Ultra` rendered in magenta, a `Latest turn` bar, and a cropped right rail showing `Outputs`, `Create a…`, `Sources`, `Attach f…`; a dictated prompt building word by word into `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.` followed by `Sure, I'll put together those hero mockups.` and `Thinking`; a Blender session with the `Global` transform header, an outliner reading `Scene Collection` → `Magnetic infinity / 1792 tiles` → objects `Tile_000_00` through `Tile_001_13`, a properties stack of `Transform`, `Delta Transform`, `Relations`, `Collections`, `Instancing`, `Motion Paths`, `Shading`, `Motion Blur`, `Visibility`, `Viewport Display`, `Line Art`, `Animation`, `Custom Properties`, and a timeline running `Start 1` to `End 250`; a browser address bar reading `127.0.0.1:4175` with a second site section labeled `02 / CONNECTED`, `Give them a place to meet.`, `A single space for your ideas, context and perspectives to find each other.`, and `Look inside APERTURE ↗`; and a closing shot of an openai.com page showing a starfield with `GPT` at left and `Astra` at right.**

## The model chip changes tier mid-video, and it names a model that shipped three weeks before the post

The clearest checkable fact in the clip never gets spoken. In the voice-mode frames the composer carries a model chip reading `GPT-6 Astra High`. Later, over the finished hero section, the same chip reads `GPT-6 Astra Ultra`, with `Ultra` colored magenta instead of gray. Nothing in the audio mentions either tier.

Both halves of that string check out against OpenAI's own documentation. The ChatGPT models page lists `GPT-6 Astra` first and describes it as "Our most capable model for complex work across code, apps, and research." The same page enumerates the effort options as Light, Medium, High, Extra High, Max, and Ultra, and explains that "Ultra mode goes beyond a single-agent run. It uses subagents to accelerate complex work." Wikipedia dates the model to a limited preview on September 3, 2026 and general availability on September 4, 2026. This post went up on September 25, three weeks into the model's life.

One gap survives verification. The models page states explicitly that "GPT-6 Luna supports reasoning efforts up to Max, but not Ultra," and it does not make a matching positive statement that Astra supports Ultra. The screenshot is the evidence that the pairing is real. The documentation only fails to contradict it.

## The skill he invokes by voice is a real sample skill in the openai/codex repository, and its description matches his use case word for word

The dictated prompt on screen reads:

> 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.

Whisper heard "image generation skill" and "mock-ups." The UI shows `image-generation skill` hyphenated and `mockups` closed up. The difference is cosmetic, and it matters only because the hyphenated form is closer to the actual artifact name.

OpenAI's skills documentation defines Agent Skills as packages that "package instructions, resources, and optional scripts so either product can follow a workflow reliably," built on the open agent skills standard. It lists two bundled system skills, Skill Creator and Skill Installer, and no image generation skill. That absence is misleading. The `openai/codex` repository carries a bundled sample skill named `imagegen` at `codex-rs/skills/src/assets/samples/imagegen/SKILL.md`, described as: "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."

The word "mockups" sits in the skill's own description. He asked for mockups, and the skill exists to produce mockups. The docs also explain that skills fire two ways: explicitly, by typing `@` in ChatGPT or `$` in Codex, or implicitly, when the model matches the task to a skill description. Speaking "use your image-generation skill" out loud is neither of the explicit forms. It relies on the implicit path, which is why he can name a skill without touching the keyboard.

## OpenAI ships the voice layer and the approval layer; the Blender bridge comes from somewhere the video never shows

Three of the four moving parts are first-party and documented.

The voice surface is ChatGPT Voice in the desktop app. OpenAI's docs say it supports "natural turn-taking" so you can "interrupt ChatGPT during a response, ask a follow-up, or change direction," that it runs on the GPT-Live model, and that it is available on Plus, Pro, Business, Edu, and Enterprise. The docs confirm it can "start a Codex task" and "check active tasks."

The `Approve for me` chip in the composer is also documented. OpenAI's auto-review page describes it as a permissions mode where "selecting an approved Daybreak model automatically switches the permissions control to Approve for me when that mode is available for your account and allowed by organization policy." Auto-review swaps a human approver for a separate reviewer agent at the sandbox boundary, keeping the same network and filesystem limits. The page calls it "a reviewer swap, not a permission grant." Turning that on is what makes a long unattended agent run practical, and it is the setting that quietly does the most work in this demo.

The Blender step has no first-party equivalent. He says:

> So I had Codex use Blender for me. I've never used Blender before, but it handled everything.

Blender appears in the frames as a running desktop session with a populated outliner, so something drove it. OpenAI publishes no Blender integration. Every Codex-to-Blender path that turns up in search is a community MCP server or a third-party agent skill. The clip cuts from the voice surface straight to a finished 1,792-tile scene and never shows the connection. A viewer who tries to reproduce this stalls at exactly that cut.

## The site he "deployed" is running on localhost, and the transcript claims a step the frames do not contain

Three separate frames show the browser address bar reading `127.0.0.1:4175`. That is a loopback address on a port in the range Vite hands out for local dev servers. The site rendering there is the finished APERTURE page with the working `02 / CONNECTED` scroll section.

The transcript says:

> I refined it. I deployed it. I created everything through Codex's new voice chat.

No frame shows a deployment. No frame shows a public hostname, a build log, a hosting dashboard, or a non-loopback URL. Every shot of the running site is local. The refinement claim is supported, since the hero sculpture visibly changes state across frames from intact torus to scattered tiles to reassembled infinity loop under the `Reset` and `Reassemble ↗` controls. The deployment claim rests on the narration alone.

The Blender evidence is stronger and more specific than the narration suggests. The outliner label reads `Magnetic infinity / 1792 tiles`, and the individual objects are named `Tile_000_00` upward in a two-index scheme, which is the naming a script produces rather than a human clicking through the UI. The timeline runs `Start 1` to `End 250`, Blender's default 250-frame range left untouched. Those details corroborate that code generated the scene. They say nothing about who wrote the code or through what channel.

## The hashtag is the disclosure, and the engagement numbers are small for a partner post

`#ChatGPT_Partner` is the entire caption apart from the `@ChatGPT` mention. It is a paid-partnership disclosure, required of US influencers by the Federal Trade Commission when they have a material connection to an advertiser.

The tag belongs to an active campaign. HypeAuditor data cited by AndroidHeadlines counts sponsored Instagram posts carrying `#chatgptpartner` or `#chatgpt_partner` rising from 61 in June to 122 in July to 141 in August 2026. The same report says OpenAI hired Charles Porch, formerly Instagram's head of partnerships, as VP of Global Creative Partnerships, and engaged the agency Viral Nation to run creator campaigns at scale. Most of that campaign targets parenting, fitness, travel, and education. A Codex and Blender workflow is an outlier in it.

At capture the post held 2,344 views against 91 likes, 63 saves, 16 reposts, and 1 comment. The save-to-like ratio of roughly 0.69 is high, which fits a tutorial people intend to return to. The absolute numbers are modest for a sponsored placement, which is worth holding in mind when reading the closing line, "So if you haven't tried out Astra yet, now is the time."

## Key Takeaways

- The model chip in the composer reads `GPT-6 Astra High` early in the clip and `GPT-6 Astra Ultra` later. OpenAI's models page confirms Astra exists, confirms Ultra is an effort tier that "uses subagents to accelerate complex work," and confirms Luna is excluded from Ultra.
- The spoken instruction "use your image-generation skill" maps to `imagegen`, a sample skill bundled in the `openai/codex` repository whose description explicitly covers "mockups."
- `Approve for me` is the most consequential setting visible and the one never mentioned in the audio. OpenAI documents it as an auto-review mode that replaces human approval with a reviewer agent at the sandbox boundary.
- ChatGPT Voice is documented as able to "start a Codex task" and "check active tasks." That is narrower than the clip's claim of building, refining, and deploying a site end to end without a keyboard.
- The finished site is served from `127.0.0.1:4175` in every frame that shows it. "I deployed it" has no visual support.
- **Unverified:** how Codex reached Blender. OpenAI publishes no Blender integration, the frames never show the connection, and the only candidates found are community MCP servers and third-party agent skills. Which one he used, and whether the model wrote Python against Blender's API or drove a tool bridge, cannot be determined from the video.
- **Unverified:** whether GPT-6 Astra officially supports the Ultra effort tier. The docs name Ultra as a tier and name Luna as excluded from it, without stating Astra's support either way. The on-screen chip is the only evidence.
- **Unverified:** what @chase_ai_ was paid or what deliverables the partnership specified. The disclosure hashtag establishes a paid relationship and nothing about its terms.

## Resources

- [GPT-6 Astra (Wikipedia)](https://en.wikipedia.org/wiki/GPT-6_Astra) - Dates the limited preview to September 3, 2026 and general availability to September 4, 2026, and describes the "recurrent depth" architecture.
- [Models (ChatGPT Learn)](https://learn.chatgpt.com/docs/models) - Lists GPT-6 Astra as the most capable model, enumerates the effort tiers Light through Ultra, and states that Luna tops out at Max.
- [Build skills (ChatGPT Learn)](https://learn.chatgpt.com/docs/build-skills) - Defines Agent Skills, the required `SKILL.md` layout, and the explicit (`@`, `$`) versus implicit invocation paths.
- [imagegen SKILL.md (openai/codex)](https://github.com/openai/codex/blob/main/codex-rs/skills/src/assets/samples/imagegen/SKILL.md) - The bundled sample image-generation skill, whose description names mockups as a target output.
- [ChatGPT Voice (ChatGPT Learn)](https://learn.chatgpt.com/docs/features/voice) - Confirms desktop availability, the GPT-Live model, the supported plans, and that Voice can start and check Codex tasks.
- [Auto-review (ChatGPT Learn)](https://learn.chatgpt.com/docs/sandboxing/auto-review) - Documents `Approve for me`, the reviewer-agent swap, and the `/approve` denials picker.
- [OpenAI hires influencers for ChatGPT everyday use (Android Headlines)](https://www.androidheadlines.com/2026/09/openai-hires-influencers-for-chatgpt-everyday-use.html) - Source for the `#chatgptpartner` disclosure convention, the HypeAuditor monthly post counts, the Charles Porch hire, and the Viral Nation engagement.
- [OpenAI announces rollout of GPT-6 Astra model (CNBC)](https://www.cnbc.com/2026/09/03/open-ai-astra-gpt-6-cyber.html) - Contemporaneous coverage of the September 3 rollout and the gated cyber capabilities. Listed for the record; the page returned HTTP 403 and its contents were not read directly.
