Skip to main content
Glama

Create video from text

create_video_from_text

Generates a video from a text prompt, with optional supported reference inputs and model settings. If the user has not specified an aspect ratio, choose it for where the video will be used, such as 9:16 for TikTok or Reels. To animate an existing starting image, use create_video_from_image. 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.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "end_seconds": "<end_seconds>",
      "style": "<style>"
    },
    "name": "create_video_from_text"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoOptional project name for identifying this output. Omit to use the API's default project name.Text To Video - dateTime
audioNoWhether to include audio in the video. Defaults to `false` if not specified. Audio support varies by model: * **`gemini-omni-1.2`**: Toggle-able: no additional credits for audio * **`kling-2.6`**: Not supported * **`kling-3.0`**: Toggle-able: audio adds extra credits when enabled * **`kling-4.0`**: Toggle-able: no additional credits for audio * **`ltx-2.5`**: Toggle-able: no additional credits for audio * **`minimax-h3`**: Toggle-able: no additional credits for audio * **`seedance-1.5`**: Toggle-able: audio adds extra credits when enabled * **`seedance-2.0`**: Toggle-able: no additional credits for audio * **`seedance-2.0-fast`**: Toggle-able: no additional credits for audio * **`seedance-2.0-mini`**: Toggle-able: no additional credits for audio * **`seedance-2.5`**: Toggle-able: no additional credits for audio * **`veo3.1`**: Toggle-able: audio adds extra credits when enabled * **`veo3.1-lite`**: Toggle-able: audio adds extra credits when enabled * **`wan-2.2`**: Not supported * **`wan-3.0`**: Toggle-able: no additional credits for audio
modelNoThe video generation model. With `default`, the API chooses a model using the account plan, resolution and duration. Use this option when no model was requested and it supports the intended inputs and settings. Omit an unrequested resolution so the API resolves it for the account. Preserve explicit settings and required input capabilities. Deprecated model values ending in `-audio` enable `audio`.default
styleYesInstructions describing the video to generate.
referencesNoName references without @ and refer to them as @name in style.prompt. Names must be unique, ignoring case. Maximum 50 references total. Omit for no references. Reference media for video generation. Supported models and reference media: * **`gemini-omni-1.2`**: Supports images, videos. Up to 10 references. * **`kling-3.0`**: Supports images, videos. Up to 10 references. * **`kling-4.0`**: Supports images, videos. Up to 10 references. * **`minimax-h3`**: Supports images, videos, audio. Up to 10 references. Video references must be 2–15 seconds each and 15 seconds combined, and are used in full. Audio references must be 2–15 seconds each and are used in full. * **`seedance-2.0`**: Supports images, videos, audio. Up to 10 references. * **`seedance-2.0-fast`**: Supports images, videos, audio. Up to 10 references. * **`seedance-2.0-mini`**: Supports images, videos, audio. Up to 10 references. * **`seedance-2.5`**: Supports images, videos, audio. Up to 50 references. Maximum 30 images, 10 videos and 10 audio references. The worker trims video references to 30 seconds combined and audio references to 30 seconds combined. Audio references require an image or video reference. * **`veo3.1`**: Supports images. Up to 3 references. Requires `end_seconds` of 8. * **`wan-3.0`**: Supports images, videos, audio. Up to 10 references.
resolutionNoControls the output video resolution. Defaults to `720p` on paid tiers and `480p` on free tiers. * **`gemini-omni-1.2`**: Supports 360p, 720p, 1080p, 4k. * **`kling-2.6`**: Supports 720p, 1080p. * **`kling-3.0`**: Supports 720p, 1080p, 4k. * **`kling-4.0`**: Supports 720p, 1080p. * **`ltx-2.5`**: Supports 480p, 720p, 1080p. * **`minimax-h3`**: Supports 480p, 720p, 1080p. * **`seedance-1.5`**: Supports 480p, 720p, 1080p. * **`seedance-2.0`**: Supports 480p, 720p, 1080p, 4k. * **`seedance-2.0-fast`**: Supports 480p, 720p. * **`seedance-2.0-mini`**: Supports 480p, 720p. * **`seedance-2.5`**: Supports 480p, 720p, 1080p, 4k. * **`veo3.1`**: Supports 720p, 1080p. * **`veo3.1-lite`**: Supports 720p, 1080p. * **`wan-2.2`**: Supports 480p, 720p, 1080p. * **`wan-3.0`**: Supports 480p, 720p, 1080p.
end_secondsYesThe total duration of the output video in seconds. Supported durations depend on the chosen model: * **`gemini-omni-1.2`**: any integer from 3 to 15 * **`kling-2.6`**: 5, 10 * **`kling-3.0`**: any integer from 3 to 15 * **`kling-4.0`**: any integer from 3 to 30 * **`ltx-2.5`**: any integer from 1 to 60 * **`minimax-h3`**: any integer from 1 to 30 * **`seedance-1.5`**: any integer from 4 to 12 * **`seedance-2.0`**: any integer from 4 to 15 * **`seedance-2.0-fast`**: any integer from 4 to 15 * **`seedance-2.0-mini`**: any integer from 4 to 15 * **`seedance-2.5`**: any integer from 4 to 30 * **`veo3.1`**: 4, 6, 8, 16, 24, 32, 40, 48, 56 * **`veo3.1-lite`**: 4, 6, 8, 16, 24, 32, 40, 48, 56 * **`wan-2.2`**: 3, 4, 5, 6, 7, 8, 9, 10, 15 * **`wan-3.0`**: any integer from 2 to 30 Free plans are currently limited to 10 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.
aspect_ratioNoKeep an aspect ratio the user explicitly requests. Otherwise, choose by where the output will be used: 9:16 for TikTok, Reels, Shorts, Stories or a phone screen; 16:9 for YouTube, a website, slides or TV; 1:1 for an Instagram or Facebook feed post or a profile picture. If you can't tell where the video will be used, ask before generating. If omitted, the video is 16:9. Determines the aspect ratio of the output video. * **`gemini-omni-1.2`**: Supports 16:9, 9:16. * **`kling-2.6`**: Supports 9:16, 16:9, 1:1. * **`kling-3.0`**: Supports 9:16, 16:9, 1:1. * **`kling-4.0`**: Supports 9:16, 16:9, 1:1. * **`ltx-2.5`**: Supports 9:16, 16:9, 1:1. * **`minimax-h3`**: Supports 16:9, 9:16, 1:1. * **`seedance-1.5`**: Supports 9:16, 16:9, 1:1. * **`seedance-2.0`**: Supports 9:16, 16:9, 1:1. * **`seedance-2.0-fast`**: Supports 9:16, 16:9, 1:1. * **`seedance-2.0-mini`**: Supports 9:16, 16:9, 1:1. * **`seedance-2.5`**: Supports 9:16, 16:9, 1:1. * **`veo3.1`**: Supports 9:16, 16:9. * **`veo3.1-lite`**: Supports 9:16, 16:9. * **`wan-2.2`**: Supports 9:16, 16:9, 1:1. * **`wan-3.0`**: Supports 16:9, 9:16, 1:1.
reference_audioNoAttached audio files. Set audio_index in each matching entry to its position in this list, starting at 1.
reference_imagesNoAttached image files. Set image_index in each matching entry to its position in this list, starting at 1.
reference_videosNoAttached video files. Set video_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 / resolution / description
      Previous value: -"Controls the output video resolution. Defaults to `720p` on paid tiers and `480p` on free tiers.\n\n* **`gemini-omni-1.2`**: Supports 360p, 720p, 1080p, 4k.\n* **`kling-2.6`**: Supports 720p, 1080p.\n* **`kling-3.0`**: Supports 720p, 1080p, 4k.\n* **`kling-4.0`**: Supports 720p, 1080p.\n* **`ltx-2.5`**: Supports 480p, 720p, 1080p.\n* **`minimax-h3`**: Supports 480p, 720p, 1080p.\n* **`seedance-1.5`**: Supports 480p, 720p, 1080p.\n* **`seedance-2.0`**: Supports 480p, 720p, 1080p, 4k.\n* **`seedance-2.0-fast`**: Supports 480p, 720p.\n* **`seedance-2.0-mini`**: Supports 480p, 720p.\n* **`seedance-2.5`**: Supports 480p, 720p, 1080p.\n* **`veo3.1`**: Supports 720p, 1080p.\n* **`veo3.1-lite`**: Supports 720p, 1080p.\n* **`wan-2.2`**: Supports 480p, 720p, 1080p.\n* **`wan-3.0`**: Supports 480p, 720p, 1080p.\n"New value: +"Controls the output video resolution. Defaults to `720p` on paid tiers and `480p` on free tiers.\n\n* **`gemini-omni-1.2`**: Supports 360p, 720p, 1080p, 4k.\n* **`kling-2.6`**: Supports 720p, 1080p.\n* **`kling-3.0`**: Supports 720p, 1080p, 4k.\n* **`kling-4.0`**: Supports 720p, 1080p.\n* **`ltx-2.5`**: Supports 480p, 720p, 1080p.\n* **`minimax-h3`**: Supports 480p, 720p, 1080p.\n* **`seedance-1.5`**: Supports 480p, 720p, 1080p.\n* **`seedance-2.0`**: Supports 480p, 720p, 1080p, 4k.\n* **`seedance-2.0-fast`**: Supports 480p, 720p.\n* **`seedance-2.0-mini`**: Supports 480p, 720p.\n* **`seedance-2.5`**: Supports 480p, 720p, 1080p, 4k.\n* **`veo3.1`**: Supports 720p, 1080p.\n* **`veo3.1-lite`**: Supports 720p, 1080p.\n* **`wan-2.2`**: Supports 480p, 720p, 1080p.\n* **`wan-3.0`**: Supports 480p, 720p, 1080p.\n"
  2. Changed1 schema field changed
    • changedInput schema / properties / aspect_ratio / description
      Previous value: -"Determines the aspect ratio of the output video.\n\n* **`gemini-omni-1.2`**: Supports 16:9, 9:16.\n* **`kling-2.6`**: Supports 9:16, 16:9, 1:1.\n* **`kling-3.0`**: Supports 9:16, 16:9, 1:1.\n* **`kling-4.0`**: Supports 9:16, 16:9, 1:1.\n* **`ltx-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`minimax-h3`**: Supports 16:9, 9:16, 1:1.\n* **`seedance-1.5`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-fast`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-mini`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`veo3.1`**: Supports 9:16, 16:9.\n* **`veo3.1-lite`**: Supports 9:16, 16:9.\n* **`wan-2.2`**: Supports 9:16, 16:9, 1:1.\n* **`wan-3.0`**: Supports 16:9, 9:16, 1:1.\n"New value: +"Keep an aspect ratio the user explicitly requests. Otherwise, choose by where the output will be used: 9:16 for TikTok, Reels, Shorts, Stories or a phone screen; 16:9 for YouTube, a website, slides or TV; 1:1 for an Instagram or Facebook feed post or a profile picture. If you can't tell where the video will be used, ask before generating. If omitted, the video is 16:9.\n\nDetermines the aspect ratio of the output video.\n\n* **`gemini-omni-1.2`**: Supports 16:9, 9:16.\n* **`kling-2.6`**: Supports 9:16, 16:9, 1:1.\n* **`kling-3.0`**: Supports 9:16, 16:9, 1:1.\n* **`kling-4.0`**: Supports 9:16, 16:9, 1:1.\n* **`ltx-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`minimax-h3`**: Supports 16:9, 9:16, 1:1.\n* **`seedance-1.5`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-fast`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-mini`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`veo3.1`**: Supports 9:16, 16:9.\n* **`veo3.1-lite`**: Supports 9:16, 16:9.\n* **`wan-2.2`**: Supports 9:16, 16:9, 1:1.\n* **`wan-3.0`**: Supports 16:9, 9:16, 1:1.\n"
  3. Changed1 schema field changed
    • changedInput schema / properties / end_seconds / description
      Previous value: -"The total duration of the output video in seconds. Supported durations depend on the chosen model:\n\n* **`gemini-omni-1.2`**: any integer from 3 to 15\n* **`kling-2.6`**: 5, 10\n* **`kling-3.0`**: any integer from 3 to 15\n* **`kling-4.0`**: any integer from 3 to 30\n* **`ltx-2.5`**: any integer from 1 to 60\n* **`minimax-h3`**: any integer from 1 to 30\n* **`seedance-1.5`**: any integer from 4 to 12\n* **`seedance-2.0`**: any integer from 4 to 15\n* **`seedance-2.0-fast`**: any integer from 4 to 15\n* **`seedance-2.0-mini`**: any integer from 4 to 15\n* **`seedance-2.5`**: any integer from 4 to 30\n* **`veo3.1`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`veo3.1-lite`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`wan-2.2`**: 3, 4, 5, 6, 7, 8, 9, 10, 15\n* **`wan-3.0`**: any integer from 2 to 30\n"New value: +"The total duration of the output video in seconds. Supported durations depend on the chosen model:\n\n* **`gemini-omni-1.2`**: any integer from 3 to 15\n* **`kling-2.6`**: 5, 10\n* **`kling-3.0`**: any integer from 3 to 15\n* **`kling-4.0`**: any integer from 3 to 30\n* **`ltx-2.5`**: any integer from 1 to 60\n* **`minimax-h3`**: any integer from 1 to 30\n* **`seedance-1.5`**: any integer from 4 to 12\n* **`seedance-2.0`**: any integer from 4 to 15\n* **`seedance-2.0-fast`**: any integer from 4 to 15\n* **`seedance-2.0-mini`**: any integer from 4 to 15\n* **`seedance-2.5`**: any integer from 4 to 30\n* **`veo3.1`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`veo3.1-lite`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`wan-2.2`**: 3, 4, 5, 6, 7, 8, 9, 10, 15\n* **`wan-3.0`**: any integer from 2 to 30\n\nFree plans are currently limited to 10 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."
  4. Changed8 schema fields changed
    • addedInput schema / properties / reference_audio
      Added value: +{
      +  "description": "Attached audio files. Set audio_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 / 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": 30,
      +  "minItems": 1,
      +  "type": "array"
      +}
    • addedInput schema / properties / reference_videos
      Added value: +{
      +  "description": "Attached video files. Set video_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"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "video_index"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "audio_index"
      +    ]
      +  }
      +]
    • addedInput schema / properties / references / items / properties / audio_index
      Added value: +{
      +  "description": "Position in reference_audio, starting at 1. Use exactly one attachment index or file_path.",
      +  "maximum": 10,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • 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": 30,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedInput schema / properties / references / items / properties / video_index
      Added value: +{
      +  "description": "Position in reference_videos, 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"
      +]
  5. Changed1 schema field changed
    • changedInput schema / properties / model / description
      Previous value: -"The video generation model. With `default`, paid tiers use `kling-3.0` and Free uses `ltx-2.5`. Duration, resolution, audio and reference support depend on the selected model. When no model was requested, use `default` rather than choosing a named premium model; omit an unrequested resolution so the API resolves it for the account. Preserve explicit settings and required input capabilities. Deprecated model values ending in `-audio` enable `audio`."New value: +"The video generation model. With `default`, the API chooses a model using the account plan, resolution and duration. Use this option when no model was requested and it supports the intended inputs and settings. Omit an unrequested resolution so the API resolves it for the account. Preserve explicit settings and required input capabilities. Deprecated model values ending in `-audio` enable `audio`."
  6. Changed1 schema field changed
    • changedInput schema / properties / style / properties / prompt / description
      Previous value: -"The prompt used for the video. Maximum length depends on the model that runs, in characters:\n\n* **`gemini-omni-1.2`**: 2500 characters.\n* **`kling-2.6`**: 2500 characters.\n* **`kling-3.0`**: 2500 characters.\n* **`kling-4.0`**: 10000 characters.\n* **`ltx-2.5`**: 2000 characters.\n* **`minimax-h3`**: 20000 characters.\n* **`seedance-1.5`**: 2000 characters.\n* **`seedance-2.0`**: 2000 characters.\n* **`seedance-2.0-fast`**: 2000 characters.\n* **`seedance-2.0-mini`**: 2000 characters.\n* **`seedance-2.5`**: 2000 characters.\n* **`veo3.1`**: 2500 characters.\n* **`veo3.1-lite`**: 2500 characters.\n* **`wan-2.2`**: 10000 characters.\n* **`wan-3.0`**: 10000 characters.\n\nFor `default`, the limit of the automatically selected model applies. Selection depends on subscription tier, resolution and duration. Specify an explicit model to use a known prompt limit. Prompts exceeding the effective model's limit are rejected, not truncated."New value: +"The prompt used for the video. Maximum length depends on the model that runs, in characters:\n\n* **`gemini-omni-1.2`**: 4000 characters.\n* **`kling-2.6`**: 2500 characters.\n* **`kling-3.0`**: 2500 characters.\n* **`kling-4.0`**: 10000 characters.\n* **`ltx-2.5`**: 4000 characters.\n* **`minimax-h3`**: 20000 characters.\n* **`seedance-1.5`**: 4000 characters.\n* **`seedance-2.0`**: 4000 characters.\n* **`seedance-2.0-fast`**: 4000 characters.\n* **`seedance-2.0-mini`**: 4000 characters.\n* **`seedance-2.5`**: 4000 characters.\n* **`veo3.1`**: 2500 characters.\n* **`veo3.1-lite`**: 2500 characters.\n* **`wan-2.2`**: 10000 characters.\n* **`wan-3.0`**: 10000 characters.\n\nFor `default`, the limit of the automatically selected model applies. Selection depends on subscription tier, resolution and duration. Specify an explicit model to use a known prompt limit. Prompts exceeding the effective model's limit are rejected, not truncated."
  7. Changed1 schema field changed
    • removedInput schema / properties / style / properties / prompt / maxLength
      Removed value: -20000
  8. 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 video to generate."
  9. Changed3 schema fields changed
    • changedInput schema / properties / aspect_ratio / description
      Previous value: -"Provide `aspect_ratio` to set the video’s aspect ratio. Determines the aspect ratio of the output video.\n\n* **`gemini-omni-1.2`**: Supports 16:9, 9:16.\n* **`kling-2.6`**: Supports 9:16, 16:9, 1:1.\n* **`kling-3.0`**: Supports 9:16, 16:9, 1:1.\n* **`kling-4.0`**: Supports 9:16, 16:9, 1:1.\n* **`ltx-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`minimax-h3`**: Supports 16:9, 9:16, 1:1.\n* **`seedance-1.5`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-fast`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-mini`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`veo3.1`**: Supports 9:16, 16:9.\n* **`veo3.1-lite`**: Supports 9:16, 16:9.\n* **`wan-2.2`**: Supports 9:16, 16:9, 1:1.\n* **`wan-3.0`**: Supports 16:9, 9:16, 1:1.\n"New value: +"Determines the aspect ratio of the output video.\n\n* **`gemini-omni-1.2`**: Supports 16:9, 9:16.\n* **`kling-2.6`**: Supports 9:16, 16:9, 1:1.\n* **`kling-3.0`**: Supports 9:16, 16:9, 1:1.\n* **`kling-4.0`**: Supports 9:16, 16:9, 1:1.\n* **`ltx-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`minimax-h3`**: Supports 16:9, 9:16, 1:1.\n* **`seedance-1.5`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-fast`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-mini`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`veo3.1`**: Supports 9:16, 16:9.\n* **`veo3.1-lite`**: Supports 9:16, 16:9.\n* **`wan-2.2`**: Supports 9:16, 16:9, 1:1.\n* **`wan-3.0`**: Supports 16:9, 9:16, 1:1.\n"
    • changedInput schema / properties / audio / description
      Previous value: -"Whether to include audio in the video. Defaults to `false` if not specified.\n\nAudio support varies by model:\n* **`gemini-omni-1.2`**: Not supported\n* **`kling-2.6`**: Not supported\n* **`kling-3.0`**: Toggle-able: audio adds extra credits when enabled\n* **`kling-4.0`**: Toggle-able: no additional credits for audio\n* **`ltx-2.5`**: Toggle-able: no additional credits for audio\n* **`minimax-h3`**: Toggle-able: no additional credits for audio\n* **`seedance-1.5`**: Toggle-able: audio adds extra credits when enabled\n* **`seedance-2.0`**: Toggle-able: no additional credits for audio\n* **`seedance-2.0-fast`**: Toggle-able: no additional credits for audio\n* **`seedance-2.0-mini`**: Toggle-able: no additional credits for audio\n* **`seedance-2.5`**: Toggle-able: no additional credits for audio\n* **`veo3.1`**: Toggle-able: audio adds extra credits when enabled\n* **`veo3.1-lite`**: Toggle-able: audio adds extra credits when enabled\n* **`wan-2.2`**: Not supported\n* **`wan-3.0`**: Toggle-able: no additional credits for audio\n"New value: +"Whether to include audio in the video. Defaults to `false` if not specified.\n\nAudio support varies by model:\n* **`gemini-omni-1.2`**: Toggle-able: no additional credits for audio\n* **`kling-2.6`**: Not supported\n* **`kling-3.0`**: Toggle-able: audio adds extra credits when enabled\n* **`kling-4.0`**: Toggle-able: no additional credits for audio\n* **`ltx-2.5`**: Toggle-able: no additional credits for audio\n* **`minimax-h3`**: Toggle-able: no additional credits for audio\n* **`seedance-1.5`**: Toggle-able: audio adds extra credits when enabled\n* **`seedance-2.0`**: Toggle-able: no additional credits for audio\n* **`seedance-2.0-fast`**: Toggle-able: no additional credits for audio\n* **`seedance-2.0-mini`**: Toggle-able: no additional credits for audio\n* **`seedance-2.5`**: Toggle-able: no additional credits for audio\n* **`veo3.1`**: Toggle-able: audio adds extra credits when enabled\n* **`veo3.1-lite`**: Toggle-able: audio adds extra credits when enabled\n* **`wan-2.2`**: Not supported\n* **`wan-3.0`**: Toggle-able: no additional credits for audio\n"
    • changedInput schema / properties / style / properties / prompt / description
      Previous value: -"The prompt used for the video."New value: +"The prompt used for the video. Maximum length depends on the model that runs, in characters:\n\n* **`gemini-omni-1.2`**: 2500 characters.\n* **`kling-2.6`**: 2500 characters.\n* **`kling-3.0`**: 2500 characters.\n* **`kling-4.0`**: 10000 characters.\n* **`ltx-2.5`**: 2000 characters.\n* **`minimax-h3`**: 20000 characters.\n* **`seedance-1.5`**: 2000 characters.\n* **`seedance-2.0`**: 2000 characters.\n* **`seedance-2.0-fast`**: 2000 characters.\n* **`seedance-2.0-mini`**: 2000 characters.\n* **`seedance-2.5`**: 2000 characters.\n* **`veo3.1`**: 2500 characters.\n* **`veo3.1-lite`**: 2500 characters.\n* **`wan-2.2`**: 10000 characters.\n* **`wan-3.0`**: 10000 characters.\n\nFor `default`, the limit of the automatically selected model applies. Selection depends on subscription tier, resolution and duration. Specify an explicit model to use a known prompt limit. Prompts exceeding the effective model's limit are rejected, not truncated."
  10. Changed6 schema fields changed
    • changedInput schema / properties / aspect_ratio / description
      Previous value: -"Provide `aspect_ratio` to set the video’s aspect ratio. Determines the aspect ratio of the output video.\n\n* **`gemini-omni-1.1`**: Supports 16:9, 9:16.\n* **`kling-2.6`**: Supports 9:16, 16:9, 1:1.\n* **`kling-3.0`**: Supports 9:16, 16:9, 1:1.\n* **`kling-4.0`**: Supports 9:16, 16:9, 1:1.\n* **`ltx-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`minimax-h3`**: Supports 16:9, 9:16, 1:1.\n* **`seedance-1.5`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-fast`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-mini`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`veo3.1`**: Supports 9:16, 16:9.\n* **`veo3.1-lite`**: Supports 9:16, 16:9.\n* **`wan-2.2`**: Supports 9:16, 16:9, 1:1.\n* **`wan-3.0`**: Supports 16:9, 9:16, 1:1.\n"New value: +"Provide `aspect_ratio` to set the video’s aspect ratio. Determines the aspect ratio of the output video.\n\n* **`gemini-omni-1.2`**: Supports 16:9, 9:16.\n* **`kling-2.6`**: Supports 9:16, 16:9, 1:1.\n* **`kling-3.0`**: Supports 9:16, 16:9, 1:1.\n* **`kling-4.0`**: Supports 9:16, 16:9, 1:1.\n* **`ltx-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`minimax-h3`**: Supports 16:9, 9:16, 1:1.\n* **`seedance-1.5`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-fast`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-mini`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`veo3.1`**: Supports 9:16, 16:9.\n* **`veo3.1-lite`**: Supports 9:16, 16:9.\n* **`wan-2.2`**: Supports 9:16, 16:9, 1:1.\n* **`wan-3.0`**: Supports 16:9, 9:16, 1:1.\n"
    • changedInput schema / properties / audio / description
      Previous value: -"Whether to include audio in the video. Defaults to `false` if not specified.\n\nAudio support varies by model:\n* **`gemini-omni-1.1`**: Not supported\n* **`kling-2.6`**: Not supported\n* **`kling-3.0`**: Toggle-able: audio adds extra credits when enabled\n* **`kling-4.0`**: Toggle-able: no additional credits for audio\n* **`ltx-2.5`**: Toggle-able: no additional credits for audio\n* **`minimax-h3`**: Toggle-able: no additional credits for audio\n* **`seedance-1.5`**: Toggle-able: audio adds extra credits when enabled\n* **`seedance-2.0`**: Toggle-able: no additional credits for audio\n* **`seedance-2.0-fast`**: Toggle-able: no additional credits for audio\n* **`seedance-2.0-mini`**: Toggle-able: no additional credits for audio\n* **`seedance-2.5`**: Toggle-able: no additional credits for audio\n* **`veo3.1`**: Toggle-able: audio adds extra credits when enabled\n* **`veo3.1-lite`**: Toggle-able: audio adds extra credits when enabled\n* **`wan-2.2`**: Not supported\n* **`wan-3.0`**: Toggle-able: no additional credits for audio\n"New value: +"Whether to include audio in the video. Defaults to `false` if not specified.\n\nAudio support varies by model:\n* **`gemini-omni-1.2`**: Not supported\n* **`kling-2.6`**: Not supported\n* **`kling-3.0`**: Toggle-able: audio adds extra credits when enabled\n* **`kling-4.0`**: Toggle-able: no additional credits for audio\n* **`ltx-2.5`**: Toggle-able: no additional credits for audio\n* **`minimax-h3`**: Toggle-able: no additional credits for audio\n* **`seedance-1.5`**: Toggle-able: audio adds extra credits when enabled\n* **`seedance-2.0`**: Toggle-able: no additional credits for audio\n* **`seedance-2.0-fast`**: Toggle-able: no additional credits for audio\n* **`seedance-2.0-mini`**: Toggle-able: no additional credits for audio\n* **`seedance-2.5`**: Toggle-able: no additional credits for audio\n* **`veo3.1`**: Toggle-able: audio adds extra credits when enabled\n* **`veo3.1-lite`**: Toggle-able: audio adds extra credits when enabled\n* **`wan-2.2`**: Not supported\n* **`wan-3.0`**: Toggle-able: no additional credits for audio\n"
    • changedInput schema / properties / end_seconds / description
      Previous value: -"The total duration of the output video in seconds. Supported durations depend on the chosen model:\n\n* **`gemini-omni-1.1`**: any integer from 3 to 10\n* **`kling-2.6`**: 5, 10\n* **`kling-3.0`**: any integer from 3 to 15\n* **`kling-4.0`**: any integer from 3 to 30\n* **`ltx-2.5`**: any integer from 1 to 60\n* **`minimax-h3`**: any integer from 1 to 30\n* **`seedance-1.5`**: any integer from 4 to 12\n* **`seedance-2.0`**: any integer from 4 to 15\n* **`seedance-2.0-fast`**: any integer from 4 to 15\n* **`seedance-2.0-mini`**: any integer from 4 to 15\n* **`seedance-2.5`**: any integer from 4 to 30\n* **`veo3.1`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`veo3.1-lite`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`wan-2.2`**: 3, 4, 5, 6, 7, 8, 9, 10, 15\n* **`wan-3.0`**: any integer from 2 to 30\n"New value: +"The total duration of the output video in seconds. Supported durations depend on the chosen model:\n\n* **`gemini-omni-1.2`**: any integer from 3 to 15\n* **`kling-2.6`**: 5, 10\n* **`kling-3.0`**: any integer from 3 to 15\n* **`kling-4.0`**: any integer from 3 to 30\n* **`ltx-2.5`**: any integer from 1 to 60\n* **`minimax-h3`**: any integer from 1 to 30\n* **`seedance-1.5`**: any integer from 4 to 12\n* **`seedance-2.0`**: any integer from 4 to 15\n* **`seedance-2.0-fast`**: any integer from 4 to 15\n* **`seedance-2.0-mini`**: any integer from 4 to 15\n* **`seedance-2.5`**: any integer from 4 to 30\n* **`veo3.1`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`veo3.1-lite`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`wan-2.2`**: 3, 4, 5, 6, 7, 8, 9, 10, 15\n* **`wan-3.0`**: any integer from 2 to 30\n"
    • changedInput schema / properties / model / enum
      Previous value: -[
      -  "default",
      -  "minimax-h3",
      -  "kling-4.0",
      -  "kling-3.0",
      -  "ltx-2.5",
      -  "wan-2.2",
      -  "seedance-2.5",
      -  "wan-3.0",
      -  "seedance-2.0-mini",
      -  "veo3.1",
      -  "veo3.1-lite",
      -  "seedance-2.0",
      -  "kling-2.6",
      -  "gemini-omni-1.1",
      -  "seedance-2.0-fast",
      -  "seedance-1.5",
      -  "sora-2",
      -  "ltx-2.3",
      -  "ltx-2",
      -  "kling-2.5",
      -  "kling-1.6",
      -  "seedance",
      -  "kling-2.5-audio",
      -  "veo3.1-audio"
      -]New value: +[
      +  "default",
      +  "minimax-h3",
      +  "kling-4.0",
      +  "kling-3.0",
      +  "ltx-2.5",
      +  "wan-2.2",
      +  "seedance-2.5",
      +  "wan-3.0",
      +  "seedance-2.0-mini",
      +  "veo3.1",
      +  "veo3.1-lite",
      +  "seedance-2.0",
      +  "kling-2.6",
      +  "gemini-omni-1.2",
      +  "gemini-omni-1.1",
      +  "seedance-2.0-fast",
      +  "seedance-1.5",
      +  "sora-2",
      +  "ltx-2.3",
      +  "ltx-2",
      +  "kling-2.5",
      +  "kling-1.6",
      +  "seedance",
      +  "kling-2.5-audio",
      +  "veo3.1-audio"
      +]
    • 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 50 references total. Omit for no references.\n\nReference media for video generation.\n\nSupported models and reference media:\n* **`gemini-omni-1.1`**: Supports images, videos. Up to 10 references.\n* **`kling-3.0`**: Supports images, videos. Up to 10 references.\n* **`kling-4.0`**: Supports images, videos. Up to 10 references.\n* **`minimax-h3`**: Supports images, videos, audio. Up to 10 references. Video references must be 2–15 seconds each and 15 seconds combined, and are used in full. Audio references must be 2–15 seconds each and are used in full.\n* **`seedance-2.0`**: Supports images, videos, audio. Up to 10 references.\n* **`seedance-2.0-fast`**: Supports images, videos, audio. Up to 10 references.\n* **`seedance-2.0-mini`**: Supports images, videos, audio. Up to 10 references.\n* **`seedance-2.5`**: Supports images, videos, audio. Up to 50 references. Maximum 30 images, 10 videos and 10 audio references. The worker trims video references to 30 seconds combined and audio references to 30 seconds combined. Audio references require an image or video reference.\n* **`veo3.1`**: Supports images. Up to 3 references. Requires `end_seconds` of 8.\n* **`wan-3.0`**: Supports images, videos, audio. Up to 10 references."New value: +"Name references without @ and refer to them as @name in style.prompt. Names must be unique, ignoring case. Maximum 50 references total. Omit for no references.\n\nReference media for video generation.\n\nSupported models and reference media:\n* **`gemini-omni-1.2`**: Supports images, videos. Up to 10 references.\n* **`kling-3.0`**: Supports images, videos. Up to 10 references.\n* **`kling-4.0`**: Supports images, videos. Up to 10 references.\n* **`minimax-h3`**: Supports images, videos, audio. Up to 10 references. Video references must be 2–15 seconds each and 15 seconds combined, and are used in full. Audio references must be 2–15 seconds each and are used in full.\n* **`seedance-2.0`**: Supports images, videos, audio. Up to 10 references.\n* **`seedance-2.0-fast`**: Supports images, videos, audio. Up to 10 references.\n* **`seedance-2.0-mini`**: Supports images, videos, audio. Up to 10 references.\n* **`seedance-2.5`**: Supports images, videos, audio. Up to 50 references. Maximum 30 images, 10 videos and 10 audio references. The worker trims video references to 30 seconds combined and audio references to 30 seconds combined. Audio references require an image or video reference.\n* **`veo3.1`**: Supports images. Up to 3 references. Requires `end_seconds` of 8.\n* **`wan-3.0`**: Supports images, videos, audio. Up to 10 references."
    • changedInput schema / properties / resolution / description
      Previous value: -"Controls the output video resolution. Defaults to `720p` on paid tiers and `480p` on free tiers.\n\n* **`gemini-omni-1.1`**: Supports 360p, 720p, 1080p, 4k.\n* **`kling-2.6`**: Supports 720p, 1080p.\n* **`kling-3.0`**: Supports 720p, 1080p, 4k.\n* **`kling-4.0`**: Supports 720p, 1080p.\n* **`ltx-2.5`**: Supports 480p, 720p, 1080p.\n* **`minimax-h3`**: Supports 480p, 720p, 1080p.\n* **`seedance-1.5`**: Supports 480p, 720p, 1080p.\n* **`seedance-2.0`**: Supports 480p, 720p, 1080p, 4k.\n* **`seedance-2.0-fast`**: Supports 480p, 720p.\n* **`seedance-2.0-mini`**: Supports 480p, 720p.\n* **`seedance-2.5`**: Supports 480p, 720p, 1080p.\n* **`veo3.1`**: Supports 720p, 1080p.\n* **`veo3.1-lite`**: Supports 720p, 1080p.\n* **`wan-2.2`**: Supports 480p, 720p, 1080p.\n* **`wan-3.0`**: Supports 480p, 720p, 1080p.\n"New value: +"Controls the output video resolution. Defaults to `720p` on paid tiers and `480p` on free tiers.\n\n* **`gemini-omni-1.2`**: Supports 360p, 720p, 1080p, 4k.\n* **`kling-2.6`**: Supports 720p, 1080p.\n* **`kling-3.0`**: Supports 720p, 1080p, 4k.\n* **`kling-4.0`**: Supports 720p, 1080p.\n* **`ltx-2.5`**: Supports 480p, 720p, 1080p.\n* **`minimax-h3`**: Supports 480p, 720p, 1080p.\n* **`seedance-1.5`**: Supports 480p, 720p, 1080p.\n* **`seedance-2.0`**: Supports 480p, 720p, 1080p, 4k.\n* **`seedance-2.0-fast`**: Supports 480p, 720p.\n* **`seedance-2.0-mini`**: Supports 480p, 720p.\n* **`seedance-2.5`**: Supports 480p, 720p, 1080p.\n* **`veo3.1`**: Supports 720p, 1080p.\n* **`veo3.1-lite`**: Supports 720p, 1080p.\n* **`wan-2.2`**: Supports 480p, 720p, 1080p.\n* **`wan-3.0`**: Supports 480p, 720p, 1080p.\n"
  11. Changed2 schema fields changed
    • changedInput schema / properties / references / description
      Previous value: -"Reference media for video generation. Name references without @ and refer to them as @name in style.prompt. Maximum 10 references total.\n\nSupported models and reference media:\n* **`gemini-omni-1.1`**: Supports images, videos. Up to 10 references.\n* **`kling-3.0`**: Supports images, videos.\n* **`kling-4.0`**: Supports images, videos. Up to 10 references.\n* **`minimax-h3`**: Supports images, videos, audio. Video references must be 2–15 seconds each and 15 seconds combined, and are used in full.\n* **`seedance-2.0`**: Supports images, videos, audio.\n* **`seedance-2.0-fast`**: Supports images, videos, audio.\n* **`seedance-2.0-mini`**: Supports images, videos, audio.\n* **`seedance-2.5`**: Supports images, videos, audio.\n* **`veo3.1`**: Supports images. Up to 3 references. Requires `end_seconds` of 8.\n* **`wan-3.0`**: Supports images, videos, audio."New value: +"Name references without @ and refer to them as @name in style.prompt. Names must be unique, ignoring case. Maximum 50 references total. Omit for no references.\n\nReference media for video generation.\n\nSupported models and reference media:\n* **`gemini-omni-1.1`**: Supports images, videos. Up to 10 references.\n* **`kling-3.0`**: Supports images, videos. Up to 10 references.\n* **`kling-4.0`**: Supports images, videos. Up to 10 references.\n* **`minimax-h3`**: Supports images, videos, audio. Up to 10 references. Video references must be 2–15 seconds each and 15 seconds combined, and are used in full. Audio references must be 2–15 seconds each and are used in full.\n* **`seedance-2.0`**: Supports images, videos, audio. Up to 10 references.\n* **`seedance-2.0-fast`**: Supports images, videos, audio. Up to 10 references.\n* **`seedance-2.0-mini`**: Supports images, videos, audio. Up to 10 references.\n* **`seedance-2.5`**: Supports images, videos, audio. Up to 50 references. Maximum 30 images, 10 videos and 10 audio references. The worker trims video references to 30 seconds combined and audio references to 30 seconds combined. Audio references require an image or video reference.\n* **`veo3.1`**: Supports images. Up to 3 references. Requires `end_seconds` of 8.\n* **`wan-3.0`**: Supports images, videos, audio. Up to 10 references."
    • changedInput schema / properties / references / maxItems
      Previous value: -10New value: +50
  12. Changed1 schema field changed
    • changedInput schema / properties / model / description
      Previous value: -"The video generation model. With `default`, paid tiers use `kling-3.0` and Free uses `ltx-2.5`. Duration, resolution, audio and reference support depend on the selected model. Deprecated model values ending in `-audio` enable `audio`."New value: +"The video generation model. With `default`, paid tiers use `kling-3.0` and Free uses `ltx-2.5`. Duration, resolution, audio and reference support depend on the selected model. When no model was requested, use `default` rather than choosing a named premium model; omit an unrequested resolution so the API resolves it for the account. Preserve explicit settings and required input capabilities. Deprecated model values ending in `-audio` enable `audio`."
  13. Changed1 schema field changed
    • changedInput schema / properties / end_seconds / description
      Previous value: -"The total duration of the output video in seconds. Supported durations depend on the chosen model:\n\n* **`gemini-omni-1.1`**: any integer from 3 to 10\n* **`kling-2.6`**: 5, 10\n* **`kling-3.0`**: any integer from 3 to 15\n* **`kling-4.0`**: any integer from 3 to 30\n* **`ltx-2.5`**: any integer from 1 to 60\n* **`minimax-h3`**: any integer from 1 to 30\n* **`seedance-1.5`**: any integer from 4 to 12\n* **`seedance-2.0`**: any integer from 4 to 15\n* **`seedance-2.0-fast`**: any integer from 4 to 15\n* **`seedance-2.0-mini`**: any integer from 4 to 15\n* **`seedance-2.5`**: any integer from 4 to 30\n* **`veo3.1`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`veo3.1-lite`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`wan-2.2`**: 3, 4, 5, 6, 7, 8, 9, 10, 15\n* **`wan-3.0`**: 2, 3, 4, 5, 6, 7, 8, 9, 10, 15, 20, 25, 30\n"New value: +"The total duration of the output video in seconds. Supported durations depend on the chosen model:\n\n* **`gemini-omni-1.1`**: any integer from 3 to 10\n* **`kling-2.6`**: 5, 10\n* **`kling-3.0`**: any integer from 3 to 15\n* **`kling-4.0`**: any integer from 3 to 30\n* **`ltx-2.5`**: any integer from 1 to 60\n* **`minimax-h3`**: any integer from 1 to 30\n* **`seedance-1.5`**: any integer from 4 to 12\n* **`seedance-2.0`**: any integer from 4 to 15\n* **`seedance-2.0-fast`**: any integer from 4 to 15\n* **`seedance-2.0-mini`**: any integer from 4 to 15\n* **`seedance-2.5`**: any integer from 4 to 30\n* **`veo3.1`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`veo3.1-lite`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`wan-2.2`**: 3, 4, 5, 6, 7, 8, 9, 10, 15\n* **`wan-3.0`**: any integer from 2 to 30\n"
  14. Changed6 schema fields changed
    • changedInput schema / properties / aspect_ratio / description
      Previous value: -"Provide `aspect_ratio` to set the video’s aspect ratio. Determines the aspect ratio of the output video.\n\n* **`gemini-omni-1.1`**: Supports 16:9, 9:16.\n* **`kling-2.6`**: Supports 9:16, 16:9, 1:1.\n* **`kling-3.0`**: Supports 9:16, 16:9, 1:1.\n* **`ltx-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`minimax-h3`**: Supports 16:9, 9:16, 1:1.\n* **`seedance-1.5`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-fast`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-mini`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`veo3.1`**: Supports 9:16, 16:9.\n* **`veo3.1-lite`**: Supports 9:16, 16:9.\n* **`wan-2.2`**: Supports 9:16, 16:9, 1:1.\n* **`wan-3.0`**: Supports 16:9, 9:16, 1:1.\n"New value: +"Provide `aspect_ratio` to set the video’s aspect ratio. Determines the aspect ratio of the output video.\n\n* **`gemini-omni-1.1`**: Supports 16:9, 9:16.\n* **`kling-2.6`**: Supports 9:16, 16:9, 1:1.\n* **`kling-3.0`**: Supports 9:16, 16:9, 1:1.\n* **`kling-4.0`**: Supports 9:16, 16:9, 1:1.\n* **`ltx-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`minimax-h3`**: Supports 16:9, 9:16, 1:1.\n* **`seedance-1.5`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-fast`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.0-mini`**: Supports 9:16, 16:9, 1:1.\n* **`seedance-2.5`**: Supports 9:16, 16:9, 1:1.\n* **`veo3.1`**: Supports 9:16, 16:9.\n* **`veo3.1-lite`**: Supports 9:16, 16:9.\n* **`wan-2.2`**: Supports 9:16, 16:9, 1:1.\n* **`wan-3.0`**: Supports 16:9, 9:16, 1:1.\n"
    • changedInput schema / properties / audio / description
      Previous value: -"Whether to include audio in the video. Defaults to `false` if not specified.\n\nAudio support varies by model:\n* **`gemini-omni-1.1`**: Not supported\n* **`kling-2.6`**: Not supported\n* **`kling-3.0`**: Toggle-able: audio adds extra credits when enabled\n* **`ltx-2.5`**: Toggle-able: no additional credits for audio\n* **`minimax-h3`**: Toggle-able: no additional credits for audio\n* **`seedance-1.5`**: Toggle-able: audio adds extra credits when enabled\n* **`seedance-2.0`**: Toggle-able: no additional credits for audio\n* **`seedance-2.0-fast`**: Toggle-able: no additional credits for audio\n* **`seedance-2.0-mini`**: Toggle-able: no additional credits for audio\n* **`seedance-2.5`**: Toggle-able: no additional credits for audio\n* **`veo3.1`**: Toggle-able: audio adds extra credits when enabled\n* **`veo3.1-lite`**: Toggle-able: audio adds extra credits when enabled\n* **`wan-2.2`**: Not supported\n* **`wan-3.0`**: Toggle-able: no additional credits for audio\n"New value: +"Whether to include audio in the video. Defaults to `false` if not specified.\n\nAudio support varies by model:\n* **`gemini-omni-1.1`**: Not supported\n* **`kling-2.6`**: Not supported\n* **`kling-3.0`**: Toggle-able: audio adds extra credits when enabled\n* **`kling-4.0`**: Toggle-able: no additional credits for audio\n* **`ltx-2.5`**: Toggle-able: no additional credits for audio\n* **`minimax-h3`**: Toggle-able: no additional credits for audio\n* **`seedance-1.5`**: Toggle-able: audio adds extra credits when enabled\n* **`seedance-2.0`**: Toggle-able: no additional credits for audio\n* **`seedance-2.0-fast`**: Toggle-able: no additional credits for audio\n* **`seedance-2.0-mini`**: Toggle-able: no additional credits for audio\n* **`seedance-2.5`**: Toggle-able: no additional credits for audio\n* **`veo3.1`**: Toggle-able: audio adds extra credits when enabled\n* **`veo3.1-lite`**: Toggle-able: audio adds extra credits when enabled\n* **`wan-2.2`**: Not supported\n* **`wan-3.0`**: Toggle-able: no additional credits for audio\n"
    • changedInput schema / properties / end_seconds / description
      Previous value: -"The total duration of the output video in seconds. Supported durations depend on the chosen model:\n\n* **`gemini-omni-1.1`**: any integer from 3 to 10\n* **`kling-2.6`**: 5, 10\n* **`kling-3.0`**: any integer from 3 to 15\n* **`ltx-2.5`**: any integer from 1 to 60\n* **`minimax-h3`**: any integer from 1 to 30\n* **`seedance-1.5`**: any integer from 4 to 12\n* **`seedance-2.0`**: any integer from 4 to 15\n* **`seedance-2.0-fast`**: any integer from 4 to 15\n* **`seedance-2.0-mini`**: any integer from 4 to 15\n* **`seedance-2.5`**: any integer from 4 to 30\n* **`veo3.1`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`veo3.1-lite`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`wan-2.2`**: 3, 4, 5, 6, 7, 8, 9, 10, 15\n* **`wan-3.0`**: 2, 3, 4, 5, 6, 7, 8, 9, 10, 15, 20, 25, 30\n"New value: +"The total duration of the output video in seconds. Supported durations depend on the chosen model:\n\n* **`gemini-omni-1.1`**: any integer from 3 to 10\n* **`kling-2.6`**: 5, 10\n* **`kling-3.0`**: any integer from 3 to 15\n* **`kling-4.0`**: any integer from 3 to 30\n* **`ltx-2.5`**: any integer from 1 to 60\n* **`minimax-h3`**: any integer from 1 to 30\n* **`seedance-1.5`**: any integer from 4 to 12\n* **`seedance-2.0`**: any integer from 4 to 15\n* **`seedance-2.0-fast`**: any integer from 4 to 15\n* **`seedance-2.0-mini`**: any integer from 4 to 15\n* **`seedance-2.5`**: any integer from 4 to 30\n* **`veo3.1`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`veo3.1-lite`**: 4, 6, 8, 16, 24, 32, 40, 48, 56\n* **`wan-2.2`**: 3, 4, 5, 6, 7, 8, 9, 10, 15\n* **`wan-3.0`**: 2, 3, 4, 5, 6, 7, 8, 9, 10, 15, 20, 25, 30\n"
    • changedInput schema / properties / model / enum
      Previous value: -[
      -  "default",
      -  "minimax-h3",
      -  "kling-3.0",
      -  "ltx-2.5",
      -  "wan-2.2",
      -  "seedance-2.5",
      -  "wan-3.0",
      -  "seedance-2.0-mini",
      -  "veo3.1",
      -  "veo3.1-lite",
      -  "seedance-2.0",
      -  "kling-2.6",
      -  "gemini-omni-1.1",
      -  "seedance-2.0-fast",
      -  "seedance-1.5",
      -  "sora-2",
      -  "ltx-2.3",
      -  "ltx-2",
      -  "kling-2.5",
      -  "kling-1.6",
      -  "seedance",
      -  "kling-2.5-audio",
      -  "veo3.1-audio"
      -]New value: +[
      +  "default",
      +  "minimax-h3",
      +  "kling-4.0",
      +  "kling-3.0",
      +  "ltx-2.5",
      +  "wan-2.2",
      +  "seedance-2.5",
      +  "wan-3.0",
      +  "seedance-2.0-mini",
      +  "veo3.1",
      +  "veo3.1-lite",
      +  "seedance-2.0",
      +  "kling-2.6",
      +  "gemini-omni-1.1",
      +  "seedance-2.0-fast",
      +  "seedance-1.5",
      +  "sora-2",
      +  "ltx-2.3",
      +  "ltx-2",
      +  "kling-2.5",
      +  "kling-1.6",
      +  "seedance",
      +  "kling-2.5-audio",
      +  "veo3.1-audio"
      +]
    • changedInput schema / properties / references / description
      Previous value: -"Reference media for video generation. Name references without @ and refer to them as @name in style.prompt. Maximum 10 references total.\n\nSupported models and reference media:\n* **`gemini-omni-1.1`**: Supports images, videos. Up to 10 references.\n* **`kling-3.0`**: Supports images, videos.\n* **`minimax-h3`**: Supports images, videos, audio.\n* **`seedance-2.0`**: Supports images, videos, audio.\n* **`seedance-2.0-fast`**: Supports images, videos, audio.\n* **`seedance-2.0-mini`**: Supports images, videos, audio.\n* **`seedance-2.5`**: Supports images, videos, audio.\n* **`veo3.1`**: Supports images. Up to 3 references. Requires `end_seconds` of 8.\n* **`wan-3.0`**: Supports images, videos, audio."New value: +"Reference media for video generation. Name references without @ and refer to them as @name in style.prompt. Maximum 10 references total.\n\nSupported models and reference media:\n* **`gemini-omni-1.1`**: Supports images, videos. Up to 10 references.\n* **`kling-3.0`**: Supports images, videos.\n* **`kling-4.0`**: Supports images, videos. Up to 10 references.\n* **`minimax-h3`**: Supports images, videos, audio. Video references must be 2–15 seconds each and 15 seconds combined, and are used in full.\n* **`seedance-2.0`**: Supports images, videos, audio.\n* **`seedance-2.0-fast`**: Supports images, videos, audio.\n* **`seedance-2.0-mini`**: Supports images, videos, audio.\n* **`seedance-2.5`**: Supports images, videos, audio.\n* **`veo3.1`**: Supports images. Up to 3 references. Requires `end_seconds` of 8.\n* **`wan-3.0`**: Supports images, videos, audio."
    • changedInput schema / properties / resolution / description
      Previous value: -"Controls the output video resolution. Defaults to `720p` on paid tiers and `480p` on free tiers.\n\n* **`gemini-omni-1.1`**: Supports 360p, 720p, 1080p, 4k.\n* **`kling-2.6`**: Supports 720p, 1080p.\n* **`kling-3.0`**: Supports 720p, 1080p, 4k.\n* **`ltx-2.5`**: Supports 480p, 720p, 1080p.\n* **`minimax-h3`**: Supports 480p, 720p, 1080p.\n* **`seedance-1.5`**: Supports 480p, 720p, 1080p.\n* **`seedance-2.0`**: Supports 480p, 720p, 1080p, 4k.\n* **`seedance-2.0-fast`**: Supports 480p, 720p.\n* **`seedance-2.0-mini`**: Supports 480p, 720p.\n* **`seedance-2.5`**: Supports 480p, 720p, 1080p.\n* **`veo3.1`**: Supports 720p, 1080p.\n* **`veo3.1-lite`**: Supports 720p, 1080p.\n* **`wan-2.2`**: Supports 480p, 720p, 1080p.\n* **`wan-3.0`**: Supports 480p, 720p, 1080p.\n"New value: +"Controls the output video resolution. Defaults to `720p` on paid tiers and `480p` on free tiers.\n\n* **`gemini-omni-1.1`**: Supports 360p, 720p, 1080p, 4k.\n* **`kling-2.6`**: Supports 720p, 1080p.\n* **`kling-3.0`**: Supports 720p, 1080p, 4k.\n* **`kling-4.0`**: Supports 720p, 1080p.\n* **`ltx-2.5`**: Supports 480p, 720p, 1080p.\n* **`minimax-h3`**: Supports 480p, 720p, 1080p.\n* **`seedance-1.5`**: Supports 480p, 720p, 1080p.\n* **`seedance-2.0`**: Supports 480p, 720p, 1080p, 4k.\n* **`seedance-2.0-fast`**: Supports 480p, 720p.\n* **`seedance-2.0-mini`**: Supports 480p, 720p.\n* **`seedance-2.5`**: Supports 480p, 720p, 1080p.\n* **`veo3.1`**: Supports 720p, 1080p.\n* **`veo3.1-lite`**: Supports 720p, 1080p.\n* **`wan-2.2`**: Supports 480p, 720p, 1080p.\n* **`wan-3.0`**: Supports 480p, 720p, 1080p.\n"
  15. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare the generic profile (not read-only, not idempotent, not destructive, open-world); the description adds the operationally critical facts: it runs as a background job, consumes credits, and that an account's balance does not prove a request is affordable. It further discloses that listed model/resolution/duration combinations may not be jointly available, which is behavior no annotation conveys.

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

Conciseness4/5

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

Purpose, sibling routing, and cost/async behavior are front-loaded, then operational caveats follow; essentially every sentence is actionable. It loses a point for redundancy with the schema (aspect-ratio selection guidance and reference naming are duplicated) and for a somewhat instruction-heavy, run-on tone across twelve sentences.

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

Completeness5/5

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

For an 11-parameter, nested-schema, credit-consuming async tool, the description covers the workflow end to end: pre-flight account check, settings compatibility, cost caveat, job submission, and the follow-up tool to poll. With an output schema present it need not explain return values, and it correctly spends its words on guidance instead.

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 description coverage is 100%, so the baseline is 3 and the schema already documents per-model limits extensively. The description adds value beyond that by warning that individual enumerated values are not independently valid combinations, and by directing the agent to prefer the named attachment fields for ChatGPT files and to ask when reference roles are unclear. It does restate some schema content (aspect-ratio heuristics, preserving explicit settings), which caps it below 5.

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

Purpose5/5

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

The first sentence states a specific verb and resource (generate video from a text prompt) plus the scope of optional inputs, and the third sentence explicitly routes image-to-video animation to create_video_from_image. An agent can distinguish this from create_animation, create_gif_or_short_video, and the other siblings without opening a schema.

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?

It names alternatives and the condition that selects them (create_video_from_image for an existing starting image), prescribes prerequisites (read get_account_info before choosing settings), and states the downstream step (returns a project id for wait_for_video_project). It also gives fallback behavior when inputs are ambiguous or fail, which is explicit when/when-not guidance.

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.