Your complete video creation studio, with image, speech and video tools built in.
This is a general-purpose video creation agent. It gives you access to speech, image and video generation tools in one conversation, so you can create complete videos without switching between different agents. Video is the default output, but the agent can use images and speech whenever they help produce a better result.
What you can do
Create videos from start to finish. Generate images, speech and video as needed, all within the same conversation.
Use the right tool for each step. Create an image first, turn it into a video, add narration or generate the final video directly.
Keep refining your work. Continue from previous outputs, change direction or try a different approach without starting over.
Use it for anything. Short clips, product videos, social media content, narrated videos, animated scenes or just exploring an idea.
Why use it
No agent fee. Just the standard model and platform charges.
Multiple tools in one place. You don't need to switch between separate image, speech and video agents to complete a video.
Nothing to set up: just describe what you want and start creating.
New supported image, speech and video models become available here as the platform adds them.
I love San Francisco. Surprise me with an video!
A little San Francisco magic is on its way: a cable-car ride turns into a dream as a whale made of fog swims toward the Golden Gate Bridge.
Cost of this run3,023 credits≈ $3.023Video generation (Grok Imagine Video 1.5) ×1GPT-6.1 Sol · 8,123 tokens