Elon Musk is once again stirring curiosity in the AI world, this time by showing how his platform, Grok, can create short videos complete with sound. In a post on X (formerly Twitter), Musk shared a lighthearted example that instantly grabbed attention. His prompt read: “A park ranger taking a photo of a family of four adults and children dressed in shorts and t-shirts posing by their camper van in a national park, with a smiling sasquatch standing in the woods. Everyone is eating bananas.”
The video turned the oddball prompt into a lively little scene, showing just how far Grok has come in transforming simple text into imaginative creations.
From Still Images to Talking Videos
Until recently, Grok was mostly known for generating text and still images. But Musk says the platform is now stepping into new territory with video and audio integration. Just last week, he teased that “Grok videos can now talk,” marking the tool’s shift toward more dynamic, interactive experiences.
Grok Imagine prompt:
A park ranger taking a photo of a family of four adults and children dressed in shorts and t-shirts posing by their camper van in a national park, with a smiling sasquatch standing in the woods.
With added speech prompt:
“Everyone is eating bananas” pic.twitter.com/HMy50oufiv
— Elon Musk (@elonmusk) September 7, 2025
This example gave users a taste of how Grok could evolve from static creativity to fully animated, conversational content.
What It Means for Creators
The update is still in what Musk describes as an “early beta”, meaning the features are experimental and likely to improve over time. It’s clear where this is headed – Grok isn’t aiming to be just another chatbot. By mixing video, sound, and a dash of creativity, it’s shaping up to be a handy tool for creators who want to whip up fun, original content in no time.
While it’s too early to say how Grok will compete with established AI video platforms, Musk’s quirky demonstrations suggest he’s serious about pushing creative AI into new spaces. If Grok can deliver on its promise, the days of generating talking, animated videos from just a sentence or two may soon become mainstream.
Get latest Tech and Auto news from Techlusive on our WhatsApp Channel, Facebook, X (Twitter), Instagram and YouTube.