The prompt
Score 10 of 10, Excellent
Use it when You need a few seconds of a fictional presenter saying one line to camera, for an explainer, announcement or course intro, from a video model that generates speech.
- {{presenter}}
- {{setting}}
- {{use_case}}
- {{voice}}
- {{line}}
- {{duration_seconds}}
- {{aspect_ratio}}
Full prompt and why it works
Prompt
A medium close-up, eye-level shot of {{presenter}}, standing in {{setting}}, speaking directly to the camera. The clip is for {{use_case}}, and the presenter is a fictional person created for it, not a real customer, employee or public figure. The presenter says, in a {{voice}} voice, at a calm, natural pace: "{{line}}" Action: they deliver the line with small, natural hand gestures and a relaxed expression that suits the words, then pause and smile slightly at the end. Their lip movements match the speech. Camera: a static shot on a tripod, 50mm lens look, shallow depth of field so the background is softly blurred, no cuts. Style and light: photorealistic, soft key light from one side with a gentle fill, natural skin texture, true-to-life color. The look should be clean and professional, in the style of a well-made company explainer video. Timing and format: {{duration_seconds}} seconds, one continuous shot, {{aspect_ratio}}. Sound: only the presenter's voice, clear and present with no echo, over quiet room ambience. No music and no other voices. The frame shows only the presenter and the background, with plain clothing and no logos, captions or readable text. If anything about the action is unclear, the presenter keeps still and simply speaks the line.
Variables
- {{presenter}}
- A fictional presenter, described concretely, for example "a woman in her forties with short gray hair, wearing a navy sweater". Do not describe a real, recognizable person.
- {{setting}}
- Where they stand, for example "a bright, tidy office with plants and a window behind".
- {{use_case}}
- What the clip is for, for example "the opening of a training course". Do not use it as, or present it as, a customer testimonial.
- {{voice}}
- How the voice sounds, for example "warm, mid-range, American English".
- {{line}}
- The exact words, one or two short sentences. Allow about two words per second, so an 8-second clip holds about 15 words and a short pause.
- {{duration_seconds}}
- A clip length your video model supports; check its settings.
- {{aspect_ratio}}
- 16:9 for a web page or slide, 9:16 for vertical social video.
Why it works
- Background facts. The spoken line is in quotation marks after a sentence naming who says it, the format Google's Veo guidance gives for speech, with the sound described in its own sentences.
- Length. A static tripod shot and one short line keep the clip to one focused moment, which is where speech and lip sync hold up best.
- What to avoid. The presenter is stated to be fictional and is never presented as a real customer, since advertising rules in many countries treat a made-up testimonial as deceptive.