B-roll is the connective tissue of a video. It covers a cut, sets a mood, or gives the viewer something to look at while a voiceover explains the point. The shots that work best are usually simple: a hand, a texture, a pour, a street detail, or a slow move across a room.
This workflow is built for those insert shots. Start with a text prompt, describe one action and one camera move, and generate a short clip that can sit under a narration track or bridge two talking-head cuts.
Last updated: 2026-10-20
The workspace below is preloaded with the mode, aspect ratio, and starter prompt for this page. You can change every setting before generating.
Generation Controls
These are the shared controls across all three workflow lanes.
Uses the faster route when available.
Include synchronized audio when the provider supports it.
Task Notifications
Useful for longer queue times. We keep the current task switch separate from your future default.
We send the prompt, task page link, and a direct download shortcut when the render finishes.
Save this as your default so new tasks start with notifications already enabled.
Nothing generated yet
An insert shot has one subject and one action. Coffee pouring into a cup. Rain hitting a window. A hand turning a page. A slow pan across a desk. Keep the prompt short and specific, and avoid introducing a second action or a new location. The clip should be easy to drop into a timeline without competing with the narration.
B-roll feels wrong when the light does not match the surrounding footage. If the interview is warm and soft, ask for warm window light and shallow depth of field. If the scene is cold and clinical, ask for cooler light and harder shadows. Content is easy to replace; a mismatched color temperature is much harder to hide.
Macro shot of coffee being poured into a ceramic cup, steam rising, warm morning window light, shallow depth of field, slow motion, realistic liquid physics, cinematic color grade, simple background, no text, no watermark.
Change the liquid, the cup, and the surface to match your scene. Keep the macro framing, the shallow depth of field, and the slow motion; that combination is what makes an insert feel deliberate.
The page opens the workspace in text-to-video, image-to-video, or reference-to-video mode. That choice decides whether the model starts from words, a still image, or a set of references.
The loaded prompt describes a subject, a camera move, lighting, and a visual style. Replace the subject and setting with your own, but keep the structure so the model still has clear direction.
Generate one short clip, check the motion and subject consistency, then adjust one variable at a time. Once the look is stable, reuse the prompt with new subjects instead of starting from zero.
You do not have to read a guide, open another tab, and guess which controls matter. The workflow is already configured and the generator is directly below the explanation.
A 4 to 15 second shot is enough to judge motion, framing, and subject consistency. Iterate on a short clip first, then generate the final shot with the settings you trust.
Text, image, and reference workflows share the same task history and controls, so you can move from a still-led shot to a reference-led shot without learning a second product.
Short answers about the workflow, the inputs, and what to expect from a first generation.
B-roll covers cuts, illustrates a point, and gives the viewer visual variety while the main audio continues. Common examples are hands, products, textures, streets, rooms, and slow environmental details.
Describe the lighting, color temperature, and lens feel in the prompt. You can get close, but a generative clip will not match a specific camera perfectly. Grade it in your editor if the cut needs a tighter match.
Most inserts work at 3 to 6 seconds. Generate a slightly longer clip than you need so you have room to trim in the edit.
Review the terms of service and make sure you have the rights to any reference material you provide. You are responsible for how the output is used in client deliverables.
Turn a product photo into a short AI product video with studio lighting, slow orbits, and realistic reflections. Built for e-commerce ads.
Start creating
Turn a written scene into a cinematic AI story clip. Keep characters and locations consistent with text, image, and reference video workflows.
Start creating
Generate vertical YouTube Shorts clips with a strong opening second, centered subjects, and clean space for captions. Text-to-video in 9:16.
Start creatingOpen the B-roll workflow, describe one insert shot, and generate a clip that covers the cut without pulling attention away from the story.
