AI Video Editor

What this API does

Create the same Video Editor you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow.

Good for

• Automation and batch processing
• Adding video editor into apps, pipelines, or tools

How it works (3 steps)

1. Upload your inputs (video, image, or audio) with Generate Upload URLs and copy the file_path.
2. Send a request to create a video editor job with the basic fields.
3. Check the job status until it’s complete, then download the result from downloads.

Key options

• Inputs: usually a file, sometimes a YouTube link, depending on project type
• Resolution: free users are limited to 576px; higher plans unlock HD and larger sizes
• Extra fields: e.g. face_swap_mode, start_seconds/end_seconds, or a text prompt

Cost
Credits are only charged for the frames that actually render. You’ll see an estimate when the job is queued, and the final total after it’s done.

For detailed examples, see the product page.

POST /v1/ai-video-editor

Python

Python

from magic_hour import Client
from os import getenv

client = Client(token=getenv("API_TOKEN"))
res = client.v1.ai_video_editor.generate(
    assets={"video_file_path": "/path/to/1234.mp4"},
    end_seconds=5.0,
    style={"prompt": "Change the car color to blue"},
    name="My Video Editor video",
    start_seconds=0.0,
    wait_for_completion=True,
    download_outputs=True,
    download_directory=".",
)

import { Client } from "magic-hour";

const client = new Client({ token: process.env["API_TOKEN"]!! });
const res = await client.v1.aiVideoEditor.generate(
  {
    assets: { videoFilePath: "/path/to/1234.mp4" },
    endSeconds: 5.0,
    name: "My Video Editor video",
    startSeconds: 0.0,
    style: { prompt: "Change the car color to blue" },
  },
  {
    waitForCompletion: true,
    downloadOutputs: true,
    downloadDirectory: ".",
  },
);

package main

import (
	os "os"

	sdk "github.com/magichourhq/magic-hour-go/client"
	nullable "github.com/magichourhq/magic-hour-go/nullable"
	ai_video_editor "github.com/magichourhq/magic-hour-go/resources/v1/ai_video_editor"
	types "github.com/magichourhq/magic-hour-go/types"
)

func main() {
	client := sdk.NewClient(
		sdk.WithBearerAuth(os.Getenv("API_TOKEN")),
	)
	res, err := client.V1.AiVideoEditor.Create(ai_video_editor.CreateRequest{
		Assets: types.V1AiVideoEditorCreateBodyAssets{
			VideoFilePath: "api-assets/id/1234.mp4",
		},
		EndSeconds:   5.0,
		Name:         nullable.NewValue("My Video Editor video"),
		StartSeconds: nullable.NewValue(0.0),
		Style: types.V1AiVideoEditorCreateBodyStyle{
			Prompt: "Change the car color to blue",
		},
	})
}

let client = magic_hour::Client::default()
    .with_bearer_auth(&std::env::var("API_TOKEN").unwrap());
let res = client
    .v1()
    .ai_video_editor()
    .create(magic_hour::resources::v1::ai_video_editor::CreateRequest {
        assets: magic_hour::models::V1AiVideoEditorCreateBodyAssets {
            video_file_path: "api-assets/id/1234.mp4".to_string(),
        },
        end_seconds: 5.0,
        name: Some("My Video Editor video".to_string()),
        start_seconds: Some(0.0),
        style: magic_hour::models::V1AiVideoEditorCreateBodyStyle {
            prompt: "Change the car color to blue".to_string(),
        },
    })
    .await;

curl --request POST \
     --url https://api.magichour.ai/v1/ai-video-editor \
     --header 'accept: application/json' \
     --header 'authorization: Bearer <token>' \
     --header 'content-type: application/json' \
     --data '
{
  "name": "My Video Editor video",
  "start_seconds": 0,
  "end_seconds": 5,
  "style": {
    "prompt": "Change the car color to blue"
  },
  "assets": {
    "video_file_path": "api-assets/id/1234.mp4"
  }
}
'

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.magichour.ai/v1/ai-video-editor",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => 'My Video Editor video',
    'start_seconds' => 0,
    'end_seconds' => 5,
    'style' => [
        'prompt' => 'Change the car color to blue'
    ],
    'assets' => [
        'video_file_path' => 'api-assets/id/1234.mp4'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "accept: application/json",
    "authorization: Bearer <token>",
    "content-type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

HttpResponse<String> response = Unirest.post("https://api.magichour.ai/v1/ai-video-editor")
  .header("accept", "application/json")
  .header("content-type", "application/json")
  .header("authorization", "Bearer <token>")
  .body("{\"name\":\"My Video Editor video\",\"start_seconds\":0,\"end_seconds\":5,\"style\":{\"prompt\":\"Change the car color to blue\"},\"assets\":{\"video_file_path\":\"api-assets/id/1234.mp4\"}}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.magichour.ai/v1/ai-video-editor")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"end_seconds\": 5,\n  \"style\": {\n    \"prompt\": \"Change the car color to blue\"\n  },\n  \"assets\": {\n    \"video_file_path\": \"api-assets/id/1234.mp4\"\n  },\n  \"name\": \"My Video Editor video\",\n  \"start_seconds\": 0,\n  \"model\": \"gemini-omni\",\n  \"resolution\": \"720p\"\n}"

response = http.request(request)
puts response.read_body

200

{
  "id": "cuid-example",
  "credits_charged": 450
}

{
  "message": "Missing request body"
}

{
  "message": "Unauthorized"
}

{
  "message": "Payment required"
}

{
  "message": "Not Found"
}

{
  "message": "Unable to edit video"
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <api_key>, where <api_key> is your API key. To get your API key, go to Developer Hub and click "Create new API Key".

Body

application/json

Body

end_seconds · number<float> · required

End time of your clip in seconds. Must be greater than start_seconds. Duration must be between 3 and 10 seconds.

Required range: x >= 0.1

Example:

5

style · object · required

Show child attributes

assets · object · required

Provide the assets for video editing.

Show child attributes

name · string · default: Video Editor - dateTime

Give your video a custom name for easy identification.

Example:

"My Video Editor video"

start_seconds · number<float> · default: 0

Start time of your clip (seconds). Must be ≥ 0.

Required range: x >= 0

Example:

0

model · enum<string>

Editing model. Defaults to ltx-2.3 for free tier and gemini-omni for paid. Use ltx-2.3 for LTX video edit.

Available options: gemini-omni, ltx-2.3

Example:

"gemini-omni"

resolution · enum<string>

Output resolution. Defaults to 480p for free tier and 720p for paid. Google Omni supports 720p only; LTX-2.3 supports 480p, 720p, and 1080p.

Available options: 480p, 720p, 1080p

Example:

"720p"

Response

200

application/json

Success

Success

id · string · required

Unique ID of the video. Use it with the Get video Project API to fetch status and downloads.

Example:

"cuid-example"

credits_charged · integer · required

The amount of credits deducted from your account to generate the video. If the status is not 'complete', this value is an estimate and may be adjusted upon completion based on the actual FPS of the output video.

If video generation fails, credits will be refunded, and this field will be updated to include the refund.

Example:

450