Browse the docs

Redo AI Story pictures

Draws the scene pictures of an AI Story video you own again, in a new look and/or with new scene instructions. Every scene keeps its narration, voiceover, captions and timing, so it spends no minutes, and scene pictures cost no credits. Leave out the look (artStyleId / imageModel) to keep the current one, and sceneInstructions to keep the saved ones ("" clears them). Scenes with an animation are kept unless includeAnimated is true (their animations are removed); scenes with your own uploads or videos are always kept. Run estimate_cost (or dryRun: true) to see how many scenes would be redrawn. Takes a minute or two: wait with get_job, then check it with preview_video and render it with render_video.

Or open inClaude Code Codex Cursor Claude ChatGPT

Paste it into any AI assistant. The shortcuts open with the prompt typed in; nothing is sent until you press enter.

At a glance

Property	Value
REST	`POST https://api.clippie.ai/v1/videos/:projectId/redo-pictures`
MCP tool	`redo_ai_story_pictures`
Scope	`create`
Cost	Spends nothing, but starts a job like the other create calls and needs the `create` scope.
Limit bucket	`legacy_video` (see Rate limits)

REST
POST https://api.clippie.ai/v1/videos/:projectId/redo-pictures
MCP tool
redo_ai_story_pictures
Scope
create
Cost
Spends nothing, but starts a job like the other create calls and needs the create scope.
Limit bucket
legacy_video (see Rate limits)

Parameters

Name	In	Type	Required	Description
`projectId`	path	string	Yes	The AI Story project id: output.projectId of a create_ai_story_video job, an id from list_videos, or the id in an editor URL. 1-64 chars.
`artStyleId`	body	string	No	A look from list_art_styles: a type "style" id, or a type "stylePrompt" id (rendered with imageModel, default seedream-5.0-lite). Up to 64 chars.
`imageModel`	body	string	No	Draw the scene images with this model (from list_art_styles imageModels) instead of a named style. Included with paid plans. One of `nano-banana`, `nano-banana-2.1`, `nano-banana-pro`, `seedream-5.0-lite`, `flux-2-pro`.
`stylePromptId`	body	string	No	Style preset (a type "stylePrompt" id) for imageModel. Up to 64 chars.
`sceneInstructions`	body	string	No	How the scenes should look: directions for every scene, for some scenes ("the last scene is at sunset"), or someone never to show ("never show the prophet, only a soft glowing light"). Changes the pictures, not what is said. Up to 1000 chars.
`includeAnimated`	body	boolean	No	Also redraw scenes that have an animation. Their animations are removed. Default false.
`dryRun`	body	boolean	No	Check the request and return { estimate } (credits and minutes) without spending anything.
`webhookUrl`	body	string (URL)	No	https URL that receives job.completed / job.failed, signed with your webhook secret. Up to 2048 chars.
`Idempotency-Key`	header	string	No	Retry-safe key: a retry with the same key and body within 24 hours returns the first job instead of starting (and charging) again. The same key with a different body is a 409. MCP clients pass it as the idempotencyKey argument. 1-255 chars. MCP: `idempotencyKey`.

projectId
In:
path
Type:
string
Required:
Yes
Description:
The AI Story project id: output.projectId of a create_ai_story_video job, an id from list_videos, or the id in an editor URL. 1-64 chars.
artStyleId
In:
body
Type:
string
Required:
No
Description:
A look from list_art_styles: a type "style" id, or a type "stylePrompt" id (rendered with imageModel, default seedream-5.0-lite). Up to 64 chars.
imageModel
In:
body
Type:
string
Required:
No
Description:
Draw the scene images with this model (from list_art_styles imageModels) instead of a named style. Included with paid plans. One of nano-banana, nano-banana-2.1, nano-banana-pro, seedream-5.0-lite, flux-2-pro.
stylePromptId
In:
body
Type:
string
Required:
No
Description:
Style preset (a type "stylePrompt" id) for imageModel. Up to 64 chars.
sceneInstructions
In:
body
Type:
string
Required:
No
Description:
How the scenes should look: directions for every scene, for some scenes ("the last scene is at sunset"), or someone never to show ("never show the prophet, only a soft glowing light"). Changes the pictures, not what is said. Up to 1000 chars.
includeAnimated
In:
body
Type:
boolean
Required:
No
Description:
Also redraw scenes that have an animation. Their animations are removed. Default false.
dryRun
In:
body
Type:
boolean
Required:
No
Description:
Check the request and return { estimate } (credits and minutes) without spending anything.
webhookUrl
In:
body
Type:
string (URL)
Required:
No
Description:
https URL that receives job.completed / job.failed, signed with your webhook secret. Up to 2048 chars.
Idempotency-Key
In:
header
Type:
string
Required:
No
Description:
Retry-safe key: a retry with the same key and body within 24 hours returns the first job instead of starting (and charging) again. The same key with a different body is a 409. MCP clients pass it as the idempotencyKey argument. 1-255 chars. MCP: idempotencyKey.

Example

curl

# 1. Dry run: the exact cost, nothing is spent.
curl https://api.clippie.ai/v1/videos/PROJECT_ID/redo-pictures \
  -H "Authorization: Bearer $CLIPPIE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "artStyleId": "cinematic",
    "sceneInstructions": "Warm desert colours. The last scene is at sunset.",
    "dryRun": true
  }'
# => { "dryRun": true, "estimate": { "credits": ..., "minutes": { ... }, "wouldSucceed": true } }

# 2. The real call. Keep the key and send the same one if you retry, so it is never charged twice.
KEY=$(uuidgen)
curl https://api.clippie.ai/v1/videos/PROJECT_ID/redo-pictures \
  -H "Authorization: Bearer $CLIPPIE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $KEY" \
  -d '{
    "artStyleId": "cinematic",
    "sceneInstructions": "Warm desert colours. The last scene is at sunset."
  }'
# => 202 { "job": { "id": "job_...", "status": "queued", ... } }

redo-ai-story-pictures.mjs

import { randomUUID } from 'node:crypto';

const auth = { Authorization: `Bearer ${process.env.CLIPPIE_API_KEY}` };

const input = {
  "artStyleId": "cinematic",
  "sceneInstructions": "Warm desert colours. The last scene is at sunset."
};

async function call(body, headers = {}) {
  const res = await fetch('https://api.clippie.ai/v1/videos/PROJECT_ID/redo-pictures', {
    method: 'POST',
    headers: { ...auth, 'Content-Type': 'application/json', ...headers },
    body: JSON.stringify(body),
  });
  const json = await res.json();
  if (!res.ok) throw new Error(`${json.error.type}: ${json.error.message}`);
  return json;
}

// 1. Dry run: the exact cost, nothing is spent. Confirm it before going on.
const { estimate } = await call({ ...input, dryRun: true });
console.log(estimate); // { credits, minutes, wouldSucceed, reason }

// 2. Create. Keep the key and reuse it on retries, so a retry never charges twice.
let { job } = await call(input, { 'Idempotency-Key': randomUUID() });

// 3. Wait. Each call holds for up to 30 seconds until the job changes.
while (!['completed', 'failed', 'canceled'].includes(job.status)) {
  const res = await fetch(`https://api.clippie.ai/v1/jobs/${job.id}?wait=30`, { headers: auth });
  ({ job } = await res.json());
}
console.log(job.status, job.output);

Response

202 { job }: the job, straight away. Wait for it with Get job (?wait=30) or a webhookUrl; see Jobs and waiting. With "dryRun": true the answer is 200 { dryRun: true, estimate } and nothing is started.

202 Accepted

{
  "job": {
    "id": "job_abc123",
    "object": "job",
    "kind": "redo_ai_story_pictures",
    "status": "queued",
    "step": null,
    "progress": null,
    "input": {
      "prompt": "The lost library of Alexandria"
    },
    "output": null,
    "cost": {
      "credits": 0,
      "minutes": {
        "voiceover": 1,
        "captions": 1,
        "export": 1
      }
    },
    "error": null,
    "source": "api",
    "webhookUrl": null,
    "createdAt": "2026-10-24T12:00:00.000Z",
    "startedAt": null,
    "completedAt": null
  }
}

Dry run (200), shape only

{
  "dryRun": true,
  "estimate": {
    "credits": 0,
    "minutes": {
      "voiceover": 0,
      "captions": 0,
      "export": 0
    },
    "wouldSucceed": true
  }
}

From an MCP client

Your AI calls redo_ai_story_pictures with the same fields as JSON arguments, plus idempotencyKey instead of the header. See MCP server to connect one.

tools/call

{
  "name": "redo_ai_story_pictures",
  "arguments": {
    "projectId": "PROJECT_ID",
    "artStyleId": "cinematic",
    "sceneInstructions": "Warm desert colours. The last scene is at sunset.",
    "idempotencyKey": "a-unique-key-per-thing-you-make"
  }
}