How to make a faceless archaeological documentary short
Tell Vizard Agent the subject and the tone and it builds the whole short. Vizard Agent records the narration first, extracts frame-accurate word timings, generates the excavation visuals to fit them, and mixes the voice, music and effects at measured levels rather than normalising each stem separately.
What do you type into Vizard Agent?
Describe the register as carefully as the subject. Vizard Agent uses the tone to choose the voice, the music, the grade and the way the captions animate, so "serious archaeological science documentary" shapes far more of the result than it appears to. Stating it plainly is also what keeps a science short from drifting into speculation.
Prompt
What does Vizard Agent actually do?
A faceless documentary short is narration plus visuals plus a serious register, and everything hangs off the voice. Vizard Agent records it first, then cuts the shots and aligns the captions to its word timings, the opposite of cutting picture and adding narration later. It measures the stems too, because normalising each one and adding them together buries the voice. In the session behind this article it:
- Checked the available generation and editing tools, including effects, voices, music and captions.
- Searched for a narrator, generated the narration, transcribed it for precise word timings, and planned the scene boundaries against the voiceover segments.
- Searched stock for excavation and laboratory scenes, generated cinematic vertical visuals for the scenes it could not source, and inspected a preview grid before using any.
- Generated the music bed and the transition and scan sound effects, then built the timed voiceover track and animated captions aligned to frame-accurate word timings.
- Measured every audio stem in LUFS, mixed at exact un-normalised levels, and rendered the master.
- Reviewed a tiled sheet of quality-control frames before delivering exactly 30.0 seconds at 1080x1920 and 30fps.
When does this not work well?
A documentary makes claims about the real world, and generated visuals make no claims at all. They illustrate rather than document a real site, and the pictures will be believed, so the script has to meet a higher standard. Give Vizard Agent the dates and findings you want stated. Real sites and human remains deserve care, and thirty seconds holds one idea.
Common questions
Are the visuals real footage? Generated, with stock footage used where it fits. They illustrate the subject rather than documenting a real site.
Can it hit exactly thirty seconds? Yes. Vizard Agent conforms the narration to the timeline rather than the other way round.
Why record the narration first? Because everything else is timed to it. Vizard Agent transcribes its own narration and cuts the visuals and captions against it.