Start a render
Google Veo 3.1
Audio enabled
0:00 / 0:00

Google Veo 3.1 audio-enabled video example: city close-up

This Google Veo 3.1 text to video example shows city close-up. It highlights audio-enabled output with 8-second timing · 16:9 output.

Google Veo 3.1Text to video8s16:9Enabled$4.16
Google Veo 3.1Text to video8s16:9Audio

Prompt breakdown

Text-to-video prompt used to generate this render.

Shot 1 (0–3 s): macro close-up of one earbud rotating slowly on a wooden desk, shallow depth of field, warm desk lamp glow. Shot 2 (3–6 s): medium shot of a young professional putting the earbuds in before stepping onto…

Subject

Shot 1 (0–3 s): macro close-up of one earbud rotating slowly on a wooden desk, shallow depth of field, warm desk lamp glow. Shot 2 (3–6 s): medium shot of a young professional putting the earbuds in before stepping onto…

Workflow

Text to video

Camera

Close Up

Output

8s · 16:9

Audio

Enabled

Constraints

Text To Video, Audio Enabled, Close Up

Show full prompt

Shot 1 (0–3 s): macro close-up of one earbud rotating slowly on a wooden desk, shallow depth of field, warm desk lamp glow. Shot 2 (3–6 s): medium shot of a young professional putting the earbuds in before stepping onto a busy city street, subtle bokeh lights. Shot 3 (6–8 s): close-up of the charging case clicking shut next to a laptop, soft logo reflection in the lid. Camera: smooth dolly moves between shots, handheld feel but not shaky. Lighting: evening, warm indoors transitioning to cool street light, gentle film grain. Audio: city ambience low in the mix, soft electronic music bed, short VO line: “Block the noise, keep the focus.” No subtitles. Negative: no brand names, no on-screen text, no extreme wide angles.

Why Google Veo 3.1 fits this shot

Veo 3.1 now handles prompts, single-image animation, multi-reference guidance, first/last bridging, and clip extension in one engine.

Text prompts

Reference mode

Audio native

Key frames

Opening frame
Motion beat
Final shot

Related examples

View all examples