A faceless vertical video built from AI-generated images and a synthetic voiceover — this example narrates historical facts, but the format takes any script. Swap the topic list and schedule renders to post daily without filming anything.
{
"timeline": {
"background": "#000000",
"tracks": [
{
"clips": [
{
"asset": {
"type": "text",
"text": "{{ HEADLINE }}",
"alignment": {
"horizontal": "center",
"vertical": "center"
},
"font": {
"color": "#000000",
"family": "Montserrat ExtraBold",
"size": "60",
"lineHeight": 1
},
"width": 463,
"height": 200
},
"start": 0,
"length": "auto",
"offset": {
"x": 0,
"y": 0.309
},
"position": "center",
"fit": "none",
"scale": 1
}
]
},
{
"clips": [
{
"length": "auto",
"asset": {
"type": "image",
"src": "https://templates.shotstack.io/automated-tiktok-video-historical-facts/9bdcce84-a00f-46e5-af9c-5b1e2163fdec.png"
},
"start": 0,
"scale": 0.2,
"offset": {
"x": 0,
"y": 0.308
},
"position": "center"
}
]
},
{
"clips": [
{
"length": "end",
"asset": {
"type": "caption",
"src": "alias://VOICEOVER",
"background": {
"color": "#0091ff",
"padding": 25,
"borderRadius": 9
},
"font": {
"size": "32"
}
},
"start": 0
}
]
},
{
"clips": [
{
"fit": "none",
"scale": 1,
"length": 5,
"asset": {
"width": "768",
"height": "1280",
"type": "text-to-image",
"prompt": "{{ IMAGE_2_PROMPT }}"
},
"start": 4,
"transition": {
"out": "fade",
"in": "fade"
},
"effect": "zoomOut"
},
{
"fit": "none",
"scale": 1,
"length": 5,
"asset": {
"width": "768",
"height": "1280",
"type": "text-to-image",
"prompt": "{{ IMAGE_4_PROMPT }}"
},
"start": 12,
"transition": {
"out": "fade",
"in": "fade"
},
"effect": "slideRight"
}
]
},
{
"clips": [
{
"length": 5,
"asset": {
"width": "768",
"height": "1280",
"type": "text-to-image",
"prompt": "{{ IMAGE_1_PROMPT }}"
},
"start": 0,
"transition": {
"out": "fade"
},
"effect": "zoomIn",
"position": "center"
},
{
"fit": "none",
"scale": 1,
"length": 5,
"asset": {
"width": "768",
"height": "1280",
"type": "text-to-image",
"prompt": "{{ IMAGE_3_PROMPT }}"
},
"start": 8,
"transition": {
"out": "fade",
"in": "fade"
},
"effect": "slideLeft",
"offset": {
"x": 0.021,
"y": 0
},
"position": "center"
},
{
"fit": "none",
"scale": 1,
"length": 5,
"asset": {
"width": "768",
"height": "1280",
"type": "text-to-image",
"prompt": "{{ IMAGE_5_PROMPT }}"
},
"start": 16,
"transition": {
"out": "fade",
"in": "fade"
},
"effect": "slideUp"
}
]
},
{
"clips": [
{
"length": "auto",
"asset": {
"voice": "Amy",
"text": "{{VOICEOVER}}",
"type": "text-to-speech"
},
"start": 0,
"alias": "VOICEOVER"
}
]
}
]
},
"output": {
"format": "mp4",
"fps": 25,
"size": {
"width": 720,
"height": 1280
}
},
"merge": [
{
"find": "HEADLINE",
"replace": "Dancing Plague"
},
{
"find": "VOICEOVER",
"replace": "Did you know that in 1518, a bizarre 'dancing plague' broke out in Strasbourg? For days, people danced uncontrollably in the streets, with no known cause. Some even collapsed from exhaustion or died. Historians are still baffled by this strange event, which remains one of history's most mysterious epidemics."
},
{
"find": "IMAGE_1_PROMPT",
"replace": "Create a haunting yet realistic scene of a medieval street in Strasbourg, filled with townspeople dancing uncontrollably. The lighting should be dim and atmospheric, with shadows cast by the moonlight, highlighting the eerie and chaotic nature of the event. The background should include darkened medieval buildings and torches flickering in the distance."
},
{
"find": "IMAGE_2_PROMPT",
"replace": "Design a dramatic close-up of a group of individual dancers, exhausted but at ease, mid-movement. The focus should be on their intensity. The lighting should be soft, with subtle shadows creating depth."
},
{
"find": "IMAGE_3_PROMPT",
"replace": "Illustrate a medieval town square in Strasbourg, filled with a mix of dancing townspeople and concerned onlookers. The scene should feature warm torchlight contrasting with the cool moonlight, casting an ominous glow on the cobblestone streets. The architecture should be historically accurate, with wooden market stalls and stone buildings surrounding the square."
},
{
"find": "IMAGE_4_PROMPT",
"replace": "Generate an image of town officials and doctors standing on the edges of the scene, observing the chaos. They should look confused and distressed, holding scrolls or medieval medical instruments. The lighting should create a contrast between the torchlight and the dark, adding a sense of urgency to their expressions."
},
{
"find": "IMAGE_5_PROMPT",
"replace": "Create a surreal, almost dreamlike depiction of the dancers, with their movements becoming blurred and ghostly. The background should be dark, with dim torchlight casting long shadows, while the dancers' figures appear exaggerated and otherworldly, reflecting the mysterious nature of the event."
}
]
}Create engaging TikTok videos with this automated template that combines historical facts with AI-generated images and voiceovers. This template allows you to easily generate videos by replacing its merge fields with fascinating insights, and accompany this with a voiceover and AI generated images. This template simplifies the process with AI-powered text-to-image and text-to-speech through Shotstack Workflows. Perfect for content creators looking to help with content creation.
No account needed until you render.
Render with your AI assistant
Add the Shotstack MCP server to your editor, then paste the prompt
| Output | MP4 |
|---|---|
| Size | 720 × 1280 (9:16) |
| Length | 21s |
| Frame rate | 25 fps |
| Tracks / clips | 6 / 9 |
| Assets used | 1 caption, 1 image, 1 text, 5 text-to-image, 1 text-to-speech |
| Soundtrack | no |
| Merge fields | 7 |
Send a merge array with your values for these fields:
| Field | Default value |
|---|---|
{{ HEADLINE }} | Dancing Plague |
{{ VOICEOVER }} | Did you know that in 1518, a bizarre 'dancing plague' broke out in Strasbourg? For days, people danced uncontrollably in the streets, with no known cause. Some even collapsed from exhaustion or died. Historians are still baffled by this strange event, which remains one of history's most mysterious epidemics. |
{{ IMAGE_1_PROMPT }} | Create a haunting yet realistic scene of a medieval street in Strasbourg, filled with townspeople dancing uncontrollably. The lighting should be dim and atmospheric, with shadows cast by the moonlight, highlighting the eerie and chaotic nature of the event. The background should include darkened medieval buildings and torches flickering in the distance. |
{{ IMAGE_2_PROMPT }} | Design a dramatic close-up of a group of individual dancers, exhausted but at ease, mid-movement. The focus should be on their intensity. The lighting should be soft, with subtle shadows creating depth. |
{{ IMAGE_3_PROMPT }} | Illustrate a medieval town square in Strasbourg, filled with a mix of dancing townspeople and concerned onlookers. The scene should feature warm torchlight contrasting with the cool moonlight, casting an ominous glow on the cobblestone streets. The architecture should be historically accurate, with wooden market stalls and stone buildings surrounding the square. |
{{ IMAGE_4_PROMPT }} | Generate an image of town officials and doctors standing on the edges of the scene, observing the chaos. They should look confused and distressed, holding scrolls or medieval medical instruments. The lighting should create a contrast between the torchlight and the dark, adding a sense of urgency to their expressions. |
{{ IMAGE_5_PROMPT }} | Create a surreal, almost dreamlike depiction of the dancers, with their movements becoming blurred and ghostly. The background should be dark, with dim torchlight casting long shadows, while the dancers' figures appear exaggerated and otherworldly, reflecting the mysterious nature of the event. |
Save the JSON above as template.json, then render in the free sandbox:
# Save the JSON above as template.json, then:
curl -X POST https://api.shotstack.io/edit/stage/render \
-H "x-api-key: $SHOTSTACK_API_KEY" \
-H "Content-Type: application/json" \
-d @template.json
# Poll until status is "done", then download response.url
curl https://api.shotstack.io/edit/stage/render/RENDER_ID -H "x-api-key: $SHOTSTACK_API_KEY"import { readFileSync } from 'node:fs';
const headers = { 'x-api-key': process.env.SHOTSTACK_API_KEY, 'Content-Type': 'application/json' };
const edit = JSON.parse(readFileSync('template.json', 'utf8'));
const { response } = await fetch('https://api.shotstack.io/edit/stage/render', {
method: 'POST', headers, body: JSON.stringify(edit)
}).then((r) => r.json());
let render;
do {
await new Promise((r) => setTimeout(r, 3000));
render = (await fetch(`https://api.shotstack.io/edit/stage/render/${response.id}`, { headers }).then((r) => r.json())).response;
} while (!['done', 'failed'].includes(render.status));
console.log(render.status, render.url);import json, os, time, requests
headers = {"x-api-key": os.environ["SHOTSTACK_API_KEY"]}
with open("template.json") as f:
edit = json.load(f)
render_id = requests.post("https://api.shotstack.io/edit/stage/render", json=edit, headers=headers).json()["response"]["id"]
while True:
render = requests.get(f"https://api.shotstack.io/edit/stage/render/{render_id}", headers=headers).json()["response"]
if render["status"] in ("done", "failed"):
break
time.sleep(3)
print(render["status"], render.get("url"))npm install -g @shotstack/cli
export SHOTSTACK_API_KEY=your_sandbox_key
shotstack validate template.json # offline schema check, free
shotstack render template.json --env stage --watchSandbox renders are free and watermarked. Production: the v1 endpoint and key. SDKs
Schedule it against a topic list or feed and post a fresh short every day.
Paste into Claude, ChatGPT or Cursor — your AI assistant builds the workflow around your data.
Node.js, one render per CSV row, wired to this template's 7 merge fields. Setup steps in the header.
Guides: Bulk-create from a CSV · Webhooks · Templates endpoint · Render your first video
AI assistants: Markdown () · · · CLI skill: SKILL.md () · MCP server
Use the 7 merge fields listed above. Send a merge array with your own values for each field and the API swaps them in at render time, so one template can produce thousands of unique videos.
Yes. It renders vertical 720×1280 (9:16), the format those platforms expect. Change output.size or output.aspectRatio in the JSON if you also need a square or landscape cut.
Yes. The template uses 1 image; replace each image asset's src with a public URL of your own file (JPG, PNG or WebP). Keep the timing and effects, or adjust them per clip.
Edit the text on each text asset in the JSON. Fonts come from the timeline fonts list or the asset's font family; add your own font file URL to timeline.fonts to use a brand typeface.
