Prompt Video

Veo Video: Dialogue Scene with Audio

A Veo video prompt that stages a dim interrogation scene with two lines of spoken dialogue plus ambient clock and rain sounds, showing how to write audio.

  • 🤖 Veo
  • 🗂️ Video

Prompt by Google Cloud — Veo video generation prompt guide · Original source (opens in a new tab)

View original source (opens in a new tab) See examples
Veo Video: Dialogue Scene with Audio — prompt preview

The prompt

prompt 
A medium shot in a dimly lit interrogation room. The seasoned detective says: Your story has holes. The nervous informant, sweating under a single bare bulb, replies: I'm telling you everything I know. The only other sounds are the slow, rhythmic ticking of a wall clock and the faint sound of rain against the window

What it is

This is a text-to-video prompt for Veo. It describes a medium shot in a dimly lit interrogation room with a detective and a nervous informant. The prompt includes two spoken lines written inline after a speaker description, and it names the only other sounds: a ticking wall clock and rain against the window. It serves as a pattern for writing dialogue and background sound for Veo audio.

Who it's for

  • Developers and creators learning how to write spoken lines in Veo prompts
  • Prompt writers who want to add background and ambient sounds to generated video
  • Anyone building dialogue-driven scenes with Veo and needing a reusable template

Requirements

Requirements

  • Access to Veo video generation (the source is Veo documentation on Vertex AI)
  • A text prompt describing the shot, characters, spoken lines and ambient sounds

Examples

Interrogation room (original pattern)

Prompt
prompt
A medium shot in a dimly lit interrogation room. The seasoned detective says: Your story has holes. The nervous informant, sweating under a single bare bulb, replies: I'm telling you everything I know. The only other sounds are the slow, rhythmic ticking of a wall clock and the faint sound of rain against the window

Expected output: A tense two-person scene in which the detective and informant speak the given lines over the sound of a ticking clock and rain.

Hospital waiting room

Prompt
prompt
A medium shot in a quiet hospital waiting room at night. The tired surgeon says: The operation went well. The anxious father, gripping a paper cup of coffee, replies: Can I see her now? The only other sounds are the soft hum of fluorescent lights and the distant beeping of a heart monitor

Expected output: A subdued scene with a surgeon and a father exchanging the two lines, with light hum and monitor beeps as ambient audio.

Market stall bargaining

Prompt
prompt
A medium shot at a busy open-air spice market in the afternoon. The cheerful vendor says: Best saffron in town, just for you. The skeptical customer, holding a small jar up to the light, replies: I'll pay half. The only other sounds are the murmur of the crowd and the clink of brass scales

Expected output: A lively bargaining exchange between vendor and customer with crowd murmur and clinking scales in the background.

Pros & cons

Pros

  • Pro:Shows a simple structure: shot, speakers with lines, then ambient sounds
  • Pro:Dialogue is written inline with speaker descriptions, so it is easy to adapt
  • Pro:Explicitly naming background sounds gives control over the audio atmosphere
  • Pro:Short and easy to reuse for other scenes

Cons

  • Con:Only one example is given, so it does not cover other audio cases such as music or sound effects in depth
  • Con:The source does not state output length, resolution or how closely the audio will match the text
  • Con:Covers only two lines of dialogue, so longer conversations are not demonstrated

Tips

  • Introduce each speaker with a short description before their line so it is clear who is talking
  • Use 'says:' and 'replies:' to mark spoken lines distinctly from description
  • Use 'The only other sounds are...' to specify the ambient soundscape
  • Include visual cues like lighting and framing alongside the audio details

Variations

  • Change the setting and characters while keeping the dialogue-plus-ambience structure
  • Add more speakers or lines following the same 'says:' / 'replies:' pattern
  • Swap the ambient sounds (e.g. wind, traffic, machinery) to change the mood
  • Change the shot type (e.g. close-up instead of medium shot)