# Faceless history video with AI: 3 shots, 2 stills, the exact prompts

> A faceless history short has no presenter on screen: a voiceover carries the story over wide shots of places and objects. On August 5, 2026 we built one about the desert trade routes of the medieval Islamic world. We generated 7 vertical stills with Seedream 5.0 Pro, then 12 vertical clips with Seedance 2.0 from text alone, in two passes, and two voiceover lines with a text-to-speech preset voice. This page shows three of the clips in the order of the story, two of the stills, and what went wrong in the takes we did not keep.

Canonical page: https://twistavo.com/prompts/faceless-history-video
Updated: 2026-11-18

## Setup

- Model: Seedance 2.0 and Seedream 5.0 Pro
- Settings: Order of the short: an establishing shot of the caravan for the hook, the market, then the library, with the voiceover running over all of them. Each shot is a separate Seedance 2.0 text-to-video clip, 9:16, 720p. The first pass made 6 clips from short prompts at the duration shown under each example; the second pass made 6 shorter clips from longer prompts that add a camera move and a symbol for each scene. The clips came with Seedance native sound (wind, market noise, candle crackle) and every prompt ends with "no music", so no music track was used; the clips on this page are muted. The two voiceover lines are each a little shorter than one first-pass clip, in French, made with a preset text-to-speech voice and a style tag that ends with "starts speaking immediately". The stills were not used as start frames: they are separate images of the same scenes, useful as a thumbnail and as a fallback when a clip fails. To assemble: put the voiceover on the timeline first, cut each clip to the length of its sentence, and keep the native ambience under the voice at a low level.

- [Seedance 2.0: model facts and prices](https://twistavo.com/models/seedance-2-0)
- [Storyboard sheet prompts: plan the shots first](https://twistavo.com/prompts/storyboard-sheet)

## 1. Shot 1, the hook: a caravan on the dunes at dusk

Result: Vertical AI video made with Seedance 2.0: a vast golden desert at dusk with a small line of camels and merchants silhouetted on a dune, the camera pushing slowly forward

Image: https://twistavo.com/prompts/faceless-history-video/caravan-establishing.webp

Settings: Seedance 2.0, text to video, Aspect ratio 9:16, Duration 10 s, Resolution 720p, Native audio on (muted on this page)

```text
Cinematic vertical 9:16 establishing shot. A vast golden desert at dusk, a distant caravan of camels and merchants silhouetted on the dunes, no faces visible. Camera slowly pushes forward, warm amber light, long shadows, dust in the air. Audio: gentle desert wind, distant camel sounds, no music.
```

Tip: The first two seconds decide whether a viewer stays, and this shot carries almost no motion: the caravan stays a thin line on the horizon for the whole clip. The hook comes from the voiceover, which starts on the first frame. If you want the image to hook too, ask for a closer caravan and a stronger move; the shorter second-pass retake ("pushes forward and rises") brought the camels closer and the sun into frame.

## 2. Shot 2: the market from above

Result: Vertical AI video made with Seedance 2.0: a sunlit market street with arches, spice and fabric stalls and small figures in robes, seen from an elevated angle while the camera glides

Image: https://twistavo.com/prompts/faceless-history-video/souk-glide.webp

Settings: Seedance 2.0, text to video, Aspect ratio 9:16, Duration 10 s, Resolution 720p, Native audio on (muted on this page)

```text
Cinematic vertical 9:16 shot. A peaceful ancient Islamic souk at golden hour, merchants in robes trading spices and fabrics, seen from elevated angle, no faces visible, warm light. Camera slowly glides. Audio: soft market ambience, quiet voices distant, no music.
```

Tip: "No faces visible" is a request, not a guarantee: the crowd still has small faces in it. What keeps them unreadable is the elevated angle and the distance. For a faceless format, keep crowds far away and seen from above, and check every frame before you publish.

## 3. Shot 3: the library

Result: Vertical AI video made with Seedance 2.0: an empty library hall with tall bookshelves on both sides and light falling through a pointed window, the camera gliding forward between the shelves

Image: https://twistavo.com/prompts/faceless-history-video/library-glide.webp

Settings: Seedance 2.0, text to video, Aspect ratio 9:16, Duration 10 s, Resolution 720p, Native audio on (muted on this page)

```text
Cinematic vertical 9:16 shot. A grand ancient library with high arches and shelves of old books, warm light streaming through a window, empty, reverent. Camera slowly glides forward between shelves. Audio: soft ambient, faint page rustle, no music.
```

Tip: "A grand ancient library" came out as a European Gothic hall with pointed windows, in both passes. The model fills a vague place name with the most common picture it knows. Name the architecture and the period you want, for example horseshoe arches, carved wood and tiled floors, instead of "ancient".

## 4. Still: the same library as an image

Result: Vertical AI image made with Seedream 5.0 Pro: an empty library with high arches, wooden shelves of old books, open manuscripts on a table and warm light from a window

Image: https://twistavo.com/prompts/faceless-history-video/library-still.webp

Settings: Seedream 5.0 Pro, text to image, Aspect ratio 9:16, Resolution 1k

```text
Cinematic documentary still, 9:16 vertical. A grand ancient library with high arches, shelves of old books and manuscripts, warm light streaming through a window, reverent scholarly atmosphere, completely empty of people. No faces, no text, no watermark.
```

Tip: A still costs a small fraction of a clip, so we wrote the stills first to check the look of each scene. The still kept the same Gothic arches as the clip: when a still shows the wrong place, fix the words before you pay for the video.

## 5. Still: the market at golden hour

Result: Vertical AI image made with Seedream 5.0 Pro: a busy market street at golden hour seen from above, stalls of spices and books, merchants in long robes and domes and minarets in the distance

Image: https://twistavo.com/prompts/faceless-history-video/souk-still.webp

Settings: Seedream 5.0 Pro, text to image, Aspect ratio 9:16, Resolution 1k

```text
Cinematic documentary still, 9:16 vertical. A peaceful ancient Islamic city marketplace at golden hour, merchants and traders in modest robes trading goods, spices, books and wares, seen from elevated angle, figures in long robes, no faces visible, warm sunlight. Sense of exchange, culture and commerce. No text, no watermark.
```

Tip: The still has closer figures than the clip, and two merchants in the front are large enough to read. For a thumbnail that is fine; for a faceless channel, push the camera higher or crop.

## Notes

What we would change: the map shot of the second pass (a0daa5d1) showed a modern world map with the Americas, which does not fit a medieval story, so we left it out; ask for "a hand-drawn medieval map of the Mediterranean and the Indian Ocean" instead. Variations to try: the same seven scenes for another period (Silk Road, Hanseatic ports), a shorter cut for each sentence, as in the second pass, or a start frame from each still so the clip and the thumbnail match. Every clip and image on this page was generated with AI on August 5, 2026 with the prompt and settings shown. Results change from run to run.
