Magic Hour

AI Video Editor

ai_video_editor_create_video

MCP guidance:

Starts an async video job; returns id and credits_charged. For finished results, call wait_for_video_project with that id or poll GET /v1/video-projects/{id} until complete, error, or canceled. Results include downloads; wait helpers add exact_download_urls. Preserve signed URLs and query parameters; never append expiration metadata.
For *_file_path, use an existing Magic Hour path or the upload-URL endpoint's file_path after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure.

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)

Upload your inputs (video, image, or audio) with Generate Upload URLs and copy the file_path.
Send a request to create a video editor job with the basic fields.
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: output size and plan requirements vary by workflow and model. Some workflows derive output size from the input video.
Extra fields: e.g. face_swap_mode, start_seconds/end_seconds, or a text prompt

Cost
Credits are charged when the job is queued (credits_charged in the response). Tools billed per frame charge an estimate and settle to the frames that actually render once the job finishes; tools billed per second charge the final amount upfront. Failed jobs are refunded.

For detailed examples, see the product page.

Input Schema

Name	Required	Description	Default
`name`	No	Give your video a custom name for easy identification.	Video Editor - dateTime
`model`	No	Editing model. Defaults to LTX 2.5 for free tier and `gemini-omni-1.1` for paid. `gemini-omni` is deprecated; use `gemini-omni-1.1` instead.
`style`	Yes
`assets`	Yes	Provide the assets for video editing.
`resolution`	No	Output resolution. Defaults to `480p` for free tier and `720p` for paid. `gemini-omni-1.1` and deprecated `gemini-omni` support 720p and 1080p; LTX 2.5 supports 480p, 720p, and 1080p.
`end_seconds`	Yes	End time of your clip in seconds. Must be greater than `start_seconds`. Minimum duration depends on model: `gemini-omni-1.1`: 3s, LTX 2.5: 0.5s. Maximum duration depends on model: `gemini-omni-1.1`: 10s, LTX 2.5: 60s (30s at 1080p).
`start_seconds`	No	Start time of your clip (seconds). Must be ≥ 0.

Output Schema

Name	Required	Description	Default
`id`	Yes	Unique ID of the video. Use it with the [Get video Project API](https://docs.magichour.ai/api-reference/video-projects/get-video-details) to fetch status and downloads.
`credits_charged`	Yes	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.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 25, 2026

changedInput schema / properties / assets / properties / video_file_path / description

Previous value: -"The video to edit. This value is either\n- a direct URL to the video file\n- `file_path` field from the response of the [upload urls API](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls).\n\nSee the [file upload guide](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls#input-file) for details.\n"New value: +"The video to edit. This value is either\n- a direct URL to the file. The URL path must end in a supported file extension.\n- `file_path` field from the response of the [upload urls API](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls).\n\nSee the [file upload guide](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls#input-file) for details.\n"

changedInput schema / properties / end_seconds / description

Previous value: -"End time of your clip in seconds. Must be greater than `start_seconds`. Minimum duration depends on model: `gemini-omni-1.1`: 3s, LTX 2.5: 0.5s. Maximum duration depends on model: `gemini-omni-1.1`: 10s, LTX 2.5: 20s."New value: +"End time of your clip in seconds. Must be greater than `start_seconds`. Minimum duration depends on model: `gemini-omni-1.1`: 3s, LTX 2.5: 0.5s. Maximum duration depends on model: `gemini-omni-1.1`: 10s, LTX 2.5: 60s (30s at 1080p)."

changedInput schema / properties / model / enum

Previous value: -[
-  "gemini-omni-1.1",
-  "gemini-omni",
-  "ltx-2.5",
-  "ltx-2.3"
-]New value: +[
+  "gemini-omni-1.1",
+  "ltx-2.5",
+  "gemini-omni",
+  "ltx-2.3"
+]

Changed2 schema fields changedOct 12, 2026
- changedInput schema / properties / model / example
```
Previous value: -"gemini-omni-1.1"New value: +"ltx-2.5"
```
- changedInput schema / properties / resolution / example
```
Previous value: -"720p"New value: +"480p"
```

Changed1 schema field changedSep 29, 2026

changedInput schema / properties / end_seconds / description

Previous value: -"End time of your clip in seconds. Must be greater than `start_seconds`. Minimum duration depends on model: `gemini-omni-1.1`: 3s, LTX 2.5: 0.5s. Maximum duration depends on model: `gemini-omni-1.1`: 10s, LTX 2.5: 45s."New value: +"End time of your clip in seconds. Must be greater than `start_seconds`. Minimum duration depends on model: `gemini-omni-1.1`: 3s, LTX 2.5: 0.5s. Maximum duration depends on model: `gemini-omni-1.1`: 10s, LTX 2.5: 20s."

Changed5 schema fields changedSep 24, 2026

removedInput schema / properties / context

Removed value: -{
-  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
-  "type": "string"
-}

changedInput schema / properties / end_seconds / description

Previous value: -"End time of your clip in seconds. Must be greater than `start_seconds`. Minimum duration depends on model: `gemini-omni-1.1`: 3s, `ltx-2.3`: 0.5s. Maximum duration depends on model: `gemini-omni-1.1`: 10s, `ltx-2.3`: 45s."New value: +"End time of your clip in seconds. Must be greater than `start_seconds`. Minimum duration depends on model: `gemini-omni-1.1`: 3s, LTX 2.5: 0.5s. Maximum duration depends on model: `gemini-omni-1.1`: 10s, LTX 2.5: 45s."

changedInput schema / properties / model / description

Previous value: -"Editing model. Defaults to `ltx-2.3` for free tier and `gemini-omni-1.1` for paid. `gemini-omni` is deprecated; use `gemini-omni-1.1` instead."New value: +"Editing model. Defaults to LTX 2.5 for free tier and `gemini-omni-1.1` for paid. `gemini-omni` is deprecated; use `gemini-omni-1.1` instead."

changedInput schema / properties / model / enum

Previous value: -[
-  "gemini-omni-1.1",
-  "gemini-omni",
-  "ltx-2.3"
-]New value: +[
+  "gemini-omni-1.1",
+  "gemini-omni",
+  "ltx-2.5",
+  "ltx-2.3"
+]

changedInput schema / properties / resolution / description

Previous value: -"Output resolution. Defaults to `480p` for free tier and `720p` for paid. `gemini-omni-1.1` and deprecated `gemini-omni` support 720p and 1080p; LTX-2.3 supports 480p, 720p, and 1080p."New value: +"Output resolution. Defaults to `480p` for free tier and `720p` for paid. `gemini-omni-1.1` and deprecated `gemini-omni` support 720p and 1080p; LTX 2.5 supports 480p, 720p, and 1080p."

Changed1 schema field changedSep 11, 2026

addedInput schema / properties / context

Added value: +{
+  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
+  "type": "string"
+}

Changed5 schema fields changedSep 2, 2026

changedInput schema / properties / end_seconds / description

Previous value: -"End time of your clip in seconds. Must be greater than `start_seconds`. Minimum duration depends on model: `gemini-omni`: 3s, `ltx-2.3`: 0.5s. Maximum duration depends on model: `gemini-omni`: 10s, `ltx-2.3`: 45s."New value: +"End time of your clip in seconds. Must be greater than `start_seconds`. Minimum duration depends on model: `gemini-omni-1.1`: 3s, `ltx-2.3`: 0.5s. Maximum duration depends on model: `gemini-omni-1.1`: 10s, `ltx-2.3`: 45s."

changedInput schema / properties / model / description

Previous value: -"Editing model. Defaults to `ltx-2.3` for free tier and `gemini-omni` for paid. Use `ltx-2.3` for LTX video edit."New value: +"Editing model. Defaults to `ltx-2.3` for free tier and `gemini-omni-1.1` for paid. `gemini-omni` is deprecated; use `gemini-omni-1.1` instead."

changedInput schema / properties / model / enum

Previous value: -[
-  "gemini-omni",
-  "ltx-2.3"
-]New value: +[
+  "gemini-omni-1.1",
+  "gemini-omni",
+  "ltx-2.3"
+]

changedInput schema / properties / model / example

Previous value: -"gemini-omni"New value: +"gemini-omni-1.1"

changedInput schema / properties / resolution / description

Previous value: -"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."New value: +"Output resolution. Defaults to `480p` for free tier and `720p` for paid. `gemini-omni-1.1` and deprecated `gemini-omni` support 720p and 1080p; LTX-2.3 supports 480p, 720p, and 1080p."

First observedSep 1, 2026

TDQS

A4.3/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true): it discloses that the job is async, that credits are charged at queue time, that per-frame tools estimate then settle, and that failed jobs are refunded. It also warns about signed URL/query-parameter preservation and hotlink fetch failures — real operational constraints an agent cannot infer elsewhere.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The operative guidance (async lifecycle, wait helper, file_path rules) is correctly front-loaded, but it is padded with marketing copy — 'What this API does', 'Good for', 'Automation and batch processing', and a product-page link — that does not help an agent invoke the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Annotations, an output schema, and 86% schema coverage already carry much of the load, and the description still covers job lifecycle, polling, and cost/refund behavior. Minor inaccuracies (referencing schema-absent fields such as `face_swap_mode` and YouTube inputs, plus a stray 'Preserve signed URLs' instruction aimed at consumers) keep it short of a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 86%, so the baseline is 3; the description earns above that by explaining the `*_file_path` semantics (upload-URL `file_path` vs direct URL, hotlink risk). However, it cites fields not present in this schema (`face_swap_mode`, YouTube link input), which risks confusing parameter choice.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: create a Video Editor video programmatically, equivalent to the browser product. It is clearly distinguishable from siblings like video_to_video_create_video or ai_image_editor_create_image by the editor model and prompt-based edit framing, though it never explicitly names or excludes a sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent: after creating the job, call `wait_for_video_project` with the returned id or poll GET /v1/video-projects/{id} until complete/error/canceled. Also gives a 3-step recipe including using the upload-URL endpoint first, and states when to prefer the upload-URL endpoint over direct public URLs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Magic Hour tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?