Nate Herk | AI AutomationYouTube

GPT 5.6 Sol Made This Entire Video

5:25English23 segments1,137 words · 6 min read

Search inside any video

SavedThat transcribes your saved videos and lets you search across all of them instantly. Save this video and find any moment.

TL;DR

This video demonstrates how GPT 5.6 Soul created an entire video from a single prompt without human intervention, showcasing its capabilities and efficiency.

GPT 5.6 Soul video creationAI video productionOpenAI GPT capabilitiesvoice cloning technologycost efficiency of AI modelsautomated video editingAI-driven content generationtoken usage in AI

Chapters

  1. 0:00Introduction to GPT 5.6 Soul
    01
  2. 0:30How the Workflow Operates
    02
  3. 1:30Performance Benchmarks
    03
  4. 2:30Voice and Avatar Integration
    04
  5. 3:30Cost Analysis of Token Usage
    05
  6. 4:30Conclusion and Insights
    06

Transcript

0:00

So, I gave GBD 5.6 Soul this prompt, walked away, and when I came back, I got this. Okay, so you're looking at Nate and you're hearing Nate. But Nate never stood in front of a camera for this. He didn't record this narration, and he never opened the editor. He gave me one prompt. That's it. I'm GPT 5.6 Soul

0:17

running inside codeex on Ultra. And I controlled the workflow that created every word, cut, motion graphic, and quality check you're about to see. OpenAI released Saul Broadley today, July 9th, after a limited preview and calls it the company's strongest model yet. The bigger shift is Ultra. It coordinates four agents at once. So

0:33

coordinates four agents at once. So instead of answering one question, I could run an entire production. And I want to show you guys exactly what that means, including where I needed 11 Labs, Hen, and Hyperframes to finish the job. Saul is really, really good at long, messy work that crosses tools. OpenAI calls it the company's best coding model

0:50

calls it the company's best coding model yet. In Ultra, it scored 91.9% on Terminal Bench 2.1, up from 85.6% for GPT 5.5. On browse comp, which tests Agentic browsing, Ultra hit 92.2%. But benchmarks only explain part of what

1:04

But benchmarks only explain part of what happened here. I had to research the launch, separate verified claims from hype, inspect Nate's existing production systems, write in his spoken cadence, trigger paid APIs, wait for renders, and keep checking the result. In a small one run 13 task test on this machine, Saul

1:18

run 13 task test on this machine, Saul earned 97% of the available objective points. Seven wins, five ties, and one loss. That does not prove it wins at everything. It lined up with what I saw here. Soul was especially strong on coding and structured execution. For the voice, I broke the script into sections

1:34

voice, I broke the script into sections that each stayed under 60 seconds. Keeping the generation short made it easier to hold Nate's cloned voice consistent from beginning to end. Each section went through Nate's authorized 11 Labs voice. Then I uploaded the audio to Hen and paired it with his avatar. The API did not give me a reliable way

1:50

The API did not give me a reliable way to lock the newest motion engine. So I opened the Hen editor with browser automation, changed every clip to Avatar V, regenerated them, verified the setting, and downloaded the finished renders. Then I moved into hyperframes. Every visual was mapped to the exact phrase that triggered it. I shifted

Keep reading — 15 more segments

Sign in free to read the full transcript, save this video, and search inside everything you save.

Sign in to continue reading

Prefer the original? Watch the video

Are you the creator or rights holder of this video? Request removal of this transcript.

Related Transcripts

Never lose a moment again

Save videos from YouTube, Instagram, and TikTok. Search across all your transcripts with AI-powered semantic search.

Start Saving Videos — Free Trial