Skip to main content
Glama

Edit video

edit_video

Edits the appearance or content of a supplied video segment using a text prompt. Use with a source video, the requested changes and the clip end time. Starts a background job that costs credits; returns a project id for wait_for_video_project. Before choosing settings, read get_account_info and the current parameter constraints. A listed model, resolution, duration or count is not necessarily available together or on this account. Preserve explicit requirements and all supplied inputs; explain a genuine block instead of submitting an incompatible request. Account balance alone does not prove a request is affordable. Use the named attachment fields first for ChatGPT files. Ask which file goes where if their roles are unclear. If a file fails, ask the user to attach it again and keep the requested settings.

Input Schema

NameRequiredDescriptionDefault
nameNoOptional project name for identifying this output. Omit to use the API's default project name.Video Editor - dateTime
modelNoThe AI model to use for video editing. Defaults to `ltx-2.5` on free tiers and `gemini-omni-1.2` on paid tiers. * `gemini-omni-1.2`: Best for precise clips up to 15s, references, and high-resolution output. Requires a paid tier. * `wan-3.0`: High-quality video with native audio, long clips, and end-frame control. Requires a paid tier. * `ltx-2.5`: Fastest for general scenes, long clips, audio, and rapid iteration. * `kling-4.0`: Create cinematic videos with image and video references and optional audio. Requires a paid tier.
styleYesInstructions describing the changes to make to the source video.
videoNoAttach the video from ChatGPT for this input.
assetsNoProvide the assets for video editing.
referencesNoName references without @ and refer to them as @name in style.prompt. Names must be unique, ignoring case. Maximum 10 references total. Omit for no references. Reference images for gemini-omni-1.2, wan-3.0, kling-4.0.
resolutionNoOutput resolution. Defaults to `480p` for free tier and `720p` for paid. Supported per model: `gemini-omni-1.2`: 360p, 720p, 1080p, 4k; `wan-3.0`: 480p, 720p, 1080p; `ltx-2.5`: 480p, 720p, 1080p; `kling-4.0`: 720p, 1080p.
end_secondsYesEnd time of your clip in seconds. Must be greater than `start_seconds`. Allowed duration depends on model: `gemini-omni-1.2`: 3-15s, `wan-3.0`: 2-15s, `ltx-2.5`: 0.5-60s (30s at 1080p), `kling-4.0`: 3-30s. Free plans are currently limited to 10 seconds of clip (`end_seconds` minus `start_seconds`), enforced by the API and may change. When the user gave no duration, choose one within it. Keep an explicitly requested longer one, explain the Free limit and ask before changing it. Do not default to the source video's full length.
start_secondsNoStart time of your clip (seconds). Must be ≥ 0.
reference_imagesNoAttached image files. Set image_index in each matching entry to its position in this list, starting at 1.

Output Schema

NameRequiredDescriptionDefault
idYesUnique 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_chargedYesThe 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.

  1. Changed1 schema field changed
    • changedInput schema / properties / end_seconds / description
      Previous value: -"End time of your clip in seconds. Must be greater than `start_seconds`. Allowed duration depends on model: `gemini-omni-1.2`: 3-15s, `wan-3.0`: 2-15s, `ltx-2.5`: 0.5-60s (30s at 1080p), `kling-4.0`: 3-30s."New value: +"End time of your clip in seconds. Must be greater than `start_seconds`. Allowed duration depends on model: `gemini-omni-1.2`: 3-15s, `wan-3.0`: 2-15s, `ltx-2.5`: 0.5-60s (30s at 1080p), `kling-4.0`: 3-30s.\n\nFree plans are currently limited to 10 seconds of clip (`end_seconds` minus `start_seconds`), enforced by the API and may change. When the user gave no duration, choose one within it. Keep an explicitly requested longer one, explain the Free limit and ask before changing it. Do not default to the source video's full length."
  2. Changed8 schema fields changed
    • addedInput schema / anyOf
      Added value: +[
      +  {
      +    "required": [
      +      "video"
      +    ]
      +  },
      +  {
      +    "properties": {
      +      "assets": {
      +        "required": [
      +          "video_file_path"
      +        ]
      +      }
      +    },
      +    "required": [
      +      "assets"
      +    ]
      +  }
      +]
    • removedInput schema / properties / assets / required
      Removed value: -[
      -  "video_file_path"
      -]
    • addedInput schema / properties / reference_images
      Added value: +{
      +  "description": "Attached image files. Set image_index in each matching entry to its position in this list, starting at 1.",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "download_url": {
      +        "description": "Exact HTTPS download URL supplied for the native ChatGPT attachment, including its signed query.",
      +        "title": "Download Url",
      +        "type": "string"
      +      },
      +      "file_id": {
      +        "description": "Native ChatGPT file identifier paired with download_url; not a local filesystem path.",
      +        "title": "File Id",
      +        "type": "string"
      +      },
      +      "file_name": {
      +        "default": "",
      +        "description": "Original attachment filename, when supplied by ChatGPT.",
      +        "title": "File Name",
      +        "type": "string"
      +      },
      +      "mime_type": {
      +        "default": "",
      +        "description": "Attachment MIME type, when supplied by ChatGPT.",
      +        "title": "Mime Type",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "download_url",
      +      "file_id"
      +    ],
      +    "title": "ChatGPTFile",
      +    "type": "object"
      +  },
      +  "maxItems": 10,
      +  "minItems": 1,
      +  "type": "array"
      +}
    • addedInput schema / properties / references / items / oneOf
      Added value: +[
      +  {
      +    "required": [
      +      "file_path"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "image_index"
      +    ]
      +  }
      +]
    • addedInput schema / properties / references / items / properties / image_index
      Added value: +{
      +  "description": "Position in reference_images, starting at 1. Use exactly one attachment index or file_path.",
      +  "maximum": 10,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • changedInput schema / properties / references / items / required
      Previous value: -[
      -  "name",
      -  "file_path"
      -]New value: +[
      +  "name"
      +]
    • addedInput schema / properties / video
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Attach the video from ChatGPT for this input.",
      +  "properties": {
      +    "download_url": {
      +      "description": "Exact HTTPS download URL supplied for the native ChatGPT attachment, including its signed query.",
      +      "title": "Download Url",
      +      "type": "string"
      +    },
      +    "file_id": {
      +      "description": "Native ChatGPT file identifier paired with download_url; not a local filesystem path.",
      +      "title": "File Id",
      +      "type": "string"
      +    },
      +    "file_name": {
      +      "default": "",
      +      "description": "Original attachment filename, when supplied by ChatGPT.",
      +      "title": "File Name",
      +      "type": "string"
      +    },
      +    "mime_type": {
      +      "default": "",
      +      "description": "Attachment MIME type, when supplied by ChatGPT.",
      +      "title": "Mime Type",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "download_url",
      +    "file_id"
      +  ],
      +  "title": "ChatGPTFile",
      +  "type": "object"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "end_seconds",
      -  "style",
      -  "assets"
      -]New value: +[
      +  "end_seconds",
      +  "style"
      +]
  3. Changed3 schema fields changed
    • changedInput schema / properties / name / description
      Previous value: -"Give your video a custom name for easy identification."New value: +"Optional project name for identifying this output. Omit to use the API's default project name."
    • addedInput schema / properties / references / items / properties / name / description
      Added value: +"Reference label without @. Use @name in style.prompt to refer to this file; labels must be unique ignoring case."
    • addedInput schema / properties / style / description
      Added value: +"Instructions describing the changes to make to the source video."
  4. Changed5 schema fields changed
    • changedInput schema / properties / end_seconds / description
      Previous value: -"End time of your clip in seconds. Must be greater than `start_seconds`. Allowed duration depends on model: `gemini-omni-1.1`: 3-10s, `wan-3.0`: 2-15s, `ltx-2.5`: 0.5-60s (30s at 1080p)."New value: +"End time of your clip in seconds. Must be greater than `start_seconds`. Allowed duration depends on model: `gemini-omni-1.2`: 3-15s, `wan-3.0`: 2-15s, `ltx-2.5`: 0.5-60s (30s at 1080p), `kling-4.0`: 3-30s."
    • changedInput schema / properties / model / description
      Previous value: -"Editing model. Defaults to LTX 2.5 for free tier and `gemini-omni-1.1` for paid. `wan-3.0` requires a paid tier. `gemini-omni` is deprecated; use `gemini-omni-1.1` instead."New value: +"The AI model to use for video editing. Defaults to `ltx-2.5` on free tiers and `gemini-omni-1.2` on paid tiers.\n\n* `gemini-omni-1.2`: Best for precise clips up to 15s, references, and high-resolution output. Requires a paid tier.\n* `wan-3.0`: High-quality video with native audio, long clips, and end-frame control. Requires a paid tier.\n* `ltx-2.5`: Fastest for general scenes, long clips, audio, and rapid iteration.\n* `kling-4.0`: Create cinematic videos with image and video references and optional audio. Requires a paid tier."
    • changedInput schema / properties / model / enum
      Previous value: -[
      -  "gemini-omni-1.1",
      -  "wan-3.0",
      -  "ltx-2.5",
      -  "gemini-omni",
      -  "ltx-2.3"
      -]New value: +[
      +  "gemini-omni-1.1",
      +  "gemini-omni-1.2",
      +  "wan-3.0",
      +  "ltx-2.5",
      +  "kling-4.0",
      +  "gemini-omni",
      +  "ltx-2.3"
      +]
    • changedInput schema / properties / references / description
      Previous value: -"Name references without @ and refer to them as @name in style.prompt. Names must be unique, ignoring case. Maximum 10 references total. Omit for no references.\n\nReference images for gemini-omni-1.1, wan-3.0, gemini-omni."New value: +"Name references without @ and refer to them as @name in style.prompt. Names must be unique, ignoring case. Maximum 10 references total. Omit for no references.\n\nReference images for gemini-omni-1.2, wan-3.0, kling-4.0."
    • changedInput schema / properties / resolution / description
      Previous value: -"Output resolution. Defaults to `480p` for free tier and `720p` for paid. Supported per model: `gemini-omni-1.1`: 360p, 720p, 1080p, 4k; `wan-3.0`: 480p, 720p, 1080p; `ltx-2.5`: 480p, 720p, 1080p."New value: +"Output resolution. Defaults to `480p` for free tier and `720p` for paid. Supported per model: `gemini-omni-1.2`: 360p, 720p, 1080p, 4k; `wan-3.0`: 480p, 720p, 1080p; `ltx-2.5`: 480p, 720p, 1080p; `kling-4.0`: 720p, 1080p."
  5. Changed3 schema fields changed
    • addedInput schema / properties / references
      Added value: +{
      +  "description": "Name references without @ and refer to them as @name in style.prompt. Names must be unique, ignoring case. Maximum 10 references total. Omit for no references.\n\nReference images for gemini-omni-1.1, wan-3.0, gemini-omni.",
      +  "items": {
      +    "properties": {
      +      "file_path": {
      +        "description": "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",
      +        "example": "api-assets/id/1234.png",
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "name": {
      +        "example": "hero",
      +        "pattern": "^[A-Za-z][\\w-]*$",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "name",
      +      "file_path"
      +    ],
      +    "type": "object"
      +  },
      +  "maxItems": 10,
      +  "minItems": 0,
      +  "type": "array"
      +}
    • changedInput schema / properties / resolution / description
      Previous value: -"Output resolution. Defaults to `480p` for free tier and `720p` for paid. Supported per model: `gemini-omni-1.1`: 720p, 1080p; `wan-3.0`: 480p, 720p, 1080p; `ltx-2.5`: 480p, 720p, 1080p."New value: +"Output resolution. Defaults to `480p` for free tier and `720p` for paid. Supported per model: `gemini-omni-1.1`: 360p, 720p, 1080p, 4k; `wan-3.0`: 480p, 720p, 1080p; `ltx-2.5`: 480p, 720p, 1080p."
    • changedInput schema / properties / resolution / enum
      Previous value: -[
      -  "480p",
      -  "720p",
      -  "1080p"
      -]New value: +[
      +  "360p",
      +  "480p",
      +  "720p",
      +  "1080p",
      +  "4k"
      +]
  6. Changed4 schema fields changed
    • 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: 60s (30s at 1080p)."New value: +"End time of your clip in seconds. Must be greater than `start_seconds`. Allowed duration depends on model: `gemini-omni-1.1`: 3-10s, `wan-3.0`: 2-15s, `ltx-2.5`: 0.5-60s (30s at 1080p)."
    • changedInput schema / properties / model / description
      Previous 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."New value: +"Editing model. Defaults to LTX 2.5 for free tier and `gemini-omni-1.1` for paid. `wan-3.0` requires a paid tier. `gemini-omni` is deprecated; use `gemini-omni-1.1` instead."
    • changedInput schema / properties / model / enum
      Previous value: -[
      -  "gemini-omni-1.1",
      -  "ltx-2.5",
      -  "gemini-omni",
      -  "ltx-2.3"
      -]New value: +[
      +  "gemini-omni-1.1",
      +  "wan-3.0",
      +  "ltx-2.5",
      +  "gemini-omni",
      +  "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 2.5 supports 480p, 720p, and 1080p."New value: +"Output resolution. Defaults to `480p` for free tier and `720p` for paid. Supported per model: `gemini-omni-1.1`: 720p, 1080p; `wan-3.0`: 480p, 720p, 1080p; `ltx-2.5`: 480p, 720p, 1080p."
  7. Added

TDQS

A3.8/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing that this starts a background job that costs credits, returns a project id for polling, and that model/resolution/duration combinations are account-dependent and may not be jointly available. It also warns that balance alone does not prove affordability. Missing only error/partial-failure behavior for the job itself.

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 purpose is front-loaded, but the middle drifts into generic agent policy ("Preserve explicit requirements", "explain a genuine block", "ask which file goes where") that is loosely tied to this tool. The attachment-handling advice is tacked on at the end after the credit and job semantics, which is a less useful order.

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?

For a 10-parameter, nested-object, credit-consuming mutation with an output schema, the description covers the async lifecycle, cost, account constraints, and the required input roles. It does not need to explain return values because an output schema exists, so the remaining omission is minor.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already defines every parameter, including per-model resolution and duration limits. The description adds only a loose mapping of the required inputs (source video, requested changes, clip end time) and a note that listed options are not necessarily combinable, which is largely restating schema text. Baseline 3 applies.

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 and resource ("Edits the appearance or content of a supplied video segment using a text prompt") and names the core inputs. It never distinguishes itself from near-neighbors like restyle_video or replace_character_in_video, so an agent must infer the boundary from names alone.

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

Usage Guidelines4/5

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

Gives a concrete workflow: read get_account_info and current parameter constraints before choosing settings, and use the returned project id with wait_for_video_project. It also sets a precondition policy for attachments and blocks. It stops short of naming which sibling to pick when the request is a restyle or a character swap.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.