Reference assets

1 image
  • On the balcony table he sets a small black speaker, taps play and lets the city evening carry the sound.1
Format
9:16
Length
30s

These are the assets and settings this result used. The example video is the result, not an input.

Image to Video AI That Turns a Still Into an Ad

Black Speaker Balcony Soundtest

On the balcony table he sets a small black speaker, taps play and lets the city evening carry the sound.

Format
9:16
Length
30s

Opens the workspace with this template already selected. You can change the product, format and length.

Prompt

This is a 30-second vertical TikTok product-promotion video, filmed on a phone in an authentic UGC style. Use natural light and a realistic everyday setting, and keep the image clear throughout. Image 1 shows the product for this video. Match its appearance, color, and packaging exactly to Image 1; the product must have no legible brand text. Character: a man in his twenties, with short hair, no jewelry, wearing a light-colored shirt. The person speaks directly to the phone camera throughout in relaxed, natural American English, with a warm, conversational tone, as if recommending something good to a friend. Keep the delivery at a moderate pace, without sounding like a presenter. Shot 1 [0-3 sec] Close-up: Beside a wooden balcony table, he holds the black mini speaker up to the camera. Spoken line: “This little speaker goes everywhere with me.” Shot 2 [3-10 sec] Medium shot: He sets the speaker on the table and taps his phone. Spoken line: “It pairs with my phone in seconds.” Shot 3 [10-19 sec] Close-up: The speaker grille fills the frame as he presses the volume button; soft acoustic guitar plays from the speaker. Spoken line: “For the size, the sound is really full. Clear vocals, actual bass.” Shot 4 [19-25 sec] Medium shot: He slips the speaker into the side pocket of a backpack. Spoken line: “Fits right in my bag for the park or the beach.” Shot 5 [25-30 sec] He smiles at the camera. Spoken line: “Best small speaker I've owned. Link's below.” Audio: Natural spoken English dialogue, together with button presses, a backpack zipper, and faint acoustic guitar from the speaker. No background music. Negative prompt: background music, subtitles, on-screen text, watermarks, logos, extra fingers, deformed hands, duplicate people, blurred backgrounds, depth-of-field blur, out-of-focus backgrounds. 参考图:32_6e95e0606c0746e5a52d163692a30e9d_参考图.png 33 / TikTok 视频记录

The workspace opens with this prompt so you can change the shot, product, format and length before you generate.