What does this app create?

It creates a short Japanese street-interview style video from one uploaded portrait, with TV variety-show captions, microphone motion, and a Shibuya night interview feel.

Do users need to upload anything besides one photo?

No. The app is designed around a single portrait upload, and the interview look is already configured.

Why does the app use a fixed interview look?

The TV graphics, Japanese captions, reaction box, and street-interview composition need to stay coherent, so the default effect keeps those details tightly guided.

Does the video add new subtitles?

The video prompt explicitly asks the model to preserve existing on-screen text and not add new subtitles, captions, logos, or text.

What photos work best?

Clear adult portraits, selfies, or waist-up shots with visible facial details work best. Avoid blurry photos, covered faces, or images that already contain many text overlays.

Can the generated Japanese text be exact every time?

AI-generated text can vary. The effect is tuned for the overall Japanese TV interview look and for keeping the on-screen graphics stable in the final clip.

Effect

Select Preset

Image

Upload Image

Settings

Street Interview Video Generator

VideoCharacterVideo Effects

Upload one portrait and turn it into a street interview video

Japanese street interview videos, staged from one portrait.

Three Shibuya-style interview examples show the app's generated TV frame, portrait animation, handheld motion, and preserved broadcast-caption feel.

One upload, one interview clip.

Upload a portrait

Start with one clear selfie, headshot, or upper-body photo where the face is easy to read and identity preservation matters.

Generate the answer

Generate an 8-second interview clip with subtle facial motion, microphone movement, handheld camera feel, and stable TV graphics.

Use an adult subject photo that you own or have permission to transform.

Choose a clear face with enough shoulder or torso detail for a believable street-interview frame.

Avoid source photos that already contain lots of text, because the effect adds broadcast graphics.

Keep the default prompt fixed if you want the Japanese captions and TV layout to stay stable.

Where this street interview format works.

How to make a Japanese street interview video in three steps.

Start with one portrait and generate an 8-second Shibuya interview clip with the app's default TV-show look.

Upload a clear portrait
Use a selfie, headshot, or waist-up photo where the face is visible and the subject can plausibly fit a night street-interview frame.
Tip: Photos without heavy filters, face obstruction, or existing text usually give cleaner TV graphics.
Generate the preview, then the video
Click Generate to prepare the Japanese variety-show frame, then click Generate again to create the interview clip with Shibuya street atmosphere, telop captions, a reaction box, and a microphone in frame.
Tip: If identity changes too much, retry with a sharper source image.
Preview and export
Preview the shy interview answer, then download the result once the face, microphone, camera shake, and preserved graphics look stable.
Tip: Regenerate if the model adds unwanted text or loses the TV layout.