@shotstack/schemas 1.5.6 → 1.5.7

package/dist/api.bundled.json

@@ -1208,6 +1208,7 @@
             "audio": "#/components/schemas/AudioAsset",
             "luma": "#/components/schemas/LumaAsset",
             "caption": "#/components/schemas/CaptionAsset",
+            "rich-caption": "#/components/schemas/RichCaptionAsset",
             "html": "#/components/schemas/HtmlAsset",
             "title": "#/components/schemas/TitleAsset",
             "shape": "#/components/schemas/ShapeAsset",
@@ -1239,6 +1240,9 @@
           {
             "$ref": "#/components/schemas/CaptionAsset"
           },
+          {
+            "$ref": "#/components/schemas/RichCaptionAsset"
+          },
           {
             "$ref": "#/components/schemas/HtmlAsset"
           },
@@ -1869,6 +1873,240 @@
           "src"
         ]
       },
+      "RichCaptionAsset": {
+        "description": "The RichCaptionAsset provides word-level caption animations with rich-text styling. It supports\nkaraoke-style highlighting, word-by-word animations, and advanced typography. Use with SRT/VTT\nfiles or auto-transcription via aliases.\n",
+        "type": "object",
+        "properties": {
+          "type": {
+            "enum": [
+              "rich-caption"
+            ],
+            "default": "rich-caption",
+            "description": "The type of asset - set to `rich-caption` for rich captions.",
+            "type": "string"
+          },
+          "src": {
+            "description": "The URL to an SRT or VTT subtitles file, or an alias reference to auto-generate captions from an audio or video clip. For file URLs, the URL must be publicly accessible or include credentials. For auto-captioning, use the format `alias://clip-name` where clip-name is the alias of an audio, video, or text-to-speech clip. Mutually exclusive with `words`.",
+            "type": "string",
+            "minLength": 1,
+            "example": "alias://audio"
+          },
+          "words": {
+            "description": "Pre-provided word-level timing data. Use this instead of `src` when you have word timestamps from an external source. Mutually exclusive with `src`.",
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/WordTiming"
+            },
+            "maxItems": 100000
+          },
+          "font": {
+            "description": "Font styling properties for inactive words.",
+            "$ref": "#/components/schemas/RichTextFont"
+          },
+          "style": {
+            "description": "Text style properties including spacing, line height, and transformations.",
+            "$ref": "#/components/schemas/RichTextStyle"
+          },
+          "stroke": {
+            "description": "Text stroke (outline) properties for inactive words.",
+            "$ref": "#/components/schemas/RichTextStroke"
+          },
+          "shadow": {
+            "description": "Text shadow properties.",
+            "$ref": "#/components/schemas/RichTextShadow"
+          },
+          "background": {
+            "description": "Background styling properties for the caption bounding box.",
+            "$ref": "#/components/schemas/RichTextBackground"
+          },
+          "padding": {
+            "description": "Padding inside the caption bounding box. Can be a single number (applied to all sides) or an object with individual sides.",
+            "oneOf": [
+              {
+                "type": "number",
+                "minimum": 0,
+                "description": "Padding in pixels applied to all sides.",
+                "example": 10
+              },
+              {
+                "$ref": "#/components/schemas/RichTextAsset/properties/padding/oneOf/1"
+              }
+            ]
+          },
+          "align": {
+            "description": "Text alignment properties (horizontal and vertical).",
+            "$ref": "#/components/schemas/RichTextAlignment"
+          },
+          "active": {
+            "description": "Styling properties for the active/highlighted word. These override the base styling when a word is being spoken.",
+            "$ref": "#/components/schemas/RichCaptionActive"
+          },
+          "wordAnimation": {
+            "description": "Word-level animation properties controlling how words are highlighted or revealed.",
+            "$ref": "#/components/schemas/RichCaptionWordAnimation"
+          },
+          "position": {
+            "description": "Vertical position of the caption on screen.",
+            "type": "string",
+            "enum": [
+              "top",
+              "center",
+              "bottom"
+            ],
+            "default": "bottom",
+            "example": "bottom"
+          },
+          "maxWidth": {
+            "description": "Maximum width of the caption as a ratio of the frame width. Must be between 0.1 and 1.",
+            "type": "number",
+            "minimum": 0.1,
+            "maximum": 1,
+            "default": 0.9,
+            "example": 0.85
+          },
+          "maxLines": {
+            "description": "Maximum number of lines to display at once. Must be between 1 and 10.",
+            "type": "integer",
+            "minimum": 1,
+            "maximum": 10,
+            "default": 2,
+            "example": 2
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "WordTiming": {
+        "description": "Word-level timing information for caption animation.",
+        "type": "object",
+        "properties": {
+          "text": {
+            "description": "The word text to display.",
+            "type": "string",
+            "minLength": 1,
+            "example": "Hello"
+          },
+          "start": {
+            "description": "Start time of the word in milliseconds.",
+            "type": "number",
+            "minimum": 0,
+            "example": 0
+          },
+          "end": {
+            "description": "End time of the word in milliseconds.",
+            "type": "number",
+            "minimum": 0,
+            "example": 400
+          },
+          "confidence": {
+            "description": "Speech-to-text confidence score between 0 and 1.",
+            "type": "number",
+            "minimum": 0,
+            "maximum": 1,
+            "example": 0.98
+          }
+        },
+        "required": [
+          "text",
+          "start",
+          "end"
+        ]
+      },
+      "RichCaptionActiveFont": {
+        "description": "Font properties for the active/highlighted word.",
+        "type": "object",
+        "properties": {
+          "color": {
+            "description": "The active word color using hexadecimal color notation.",
+            "type": "string",
+            "pattern": "^#[A-Fa-f0-9]{6}$",
+            "default": "#ffff00",
+            "example": "#ffff00"
+          },
+          "background": {
+            "description": "The background color behind the active word using hexadecimal color notation.",
+            "type": "string",
+            "pattern": "^#[A-Fa-f0-9]{6}$",
+            "example": "#000000"
+          },
+          "opacity": {
+            "description": "The opacity of the active word where 1 is opaque and 0 is transparent.",
+            "type": "number",
+            "minimum": 0,
+            "maximum": 1,
+            "default": 1,
+            "example": 1
+          }
+        }
+      },
+      "RichCaptionActive": {
+        "description": "Styling properties for the active/highlighted word.",
+        "type": "object",
+        "properties": {
+          "font": {
+            "description": "Font properties for the active word.",
+            "$ref": "#/components/schemas/RichCaptionActiveFont"
+          },
+          "stroke": {
+            "description": "Stroke properties for the active word.",
+            "$ref": "#/components/schemas/RichTextStroke"
+          },
+          "scale": {
+            "description": "Scale multiplier for the active word. 1.0 is normal size, 1.2 is 20% larger.",
+            "type": "number",
+            "minimum": 0.5,
+            "maximum": 2,
+            "default": 1,
+            "example": 1.2
+          }
+        }
+      },
+      "RichCaptionWordAnimation": {
+        "description": "Word-level animation properties for caption effects.",
+        "type": "object",
+        "properties": {
+          "style": {
+            "description": "The animation style to apply to words: <ul>\n  <li>`karaoke` - Word-by-word color fill as spoken (shows all words, highlights active)</li>\n  <li>`highlight` - Word changes to active color when spoken (shows all words)</li>\n  <li>`pop` - Each word scales up when active</li>\n  <li>`fade` - Gradual opacity transition per word</li>\n  <li>`slide` - Words slide in from a direction</li>\n  <li>`bounce` - Spring animation on word appearance</li>\n  <li>`typewriter` - Words appear one by one and stay visible</li>\n  <li>`none` - No animation, all words visible immediately</li>\n</ul>",
+            "type": "string",
+            "enum": [
+              "karaoke",
+              "highlight",
+              "pop",
+              "fade",
+              "slide",
+              "bounce",
+              "typewriter",
+              "none"
+            ],
+            "default": "karaoke",
+            "example": "karaoke"
+          },
+          "speed": {
+            "description": "Animation speed multiplier. 1.0 is normal speed, 0.5 is half speed, 2.0 is double speed.",
+            "type": "number",
+            "minimum": 0.5,
+            "maximum": 2,
+            "default": 1,
+            "example": 1
+          },
+          "direction": {
+            "description": "Direction for directional animations (slide). Only applicable when style is `slide`.",
+            "type": "string",
+            "enum": [
+              "left",
+              "right",
+              "up",
+              "down"
+            ],
+            "default": "up",
+            "example": "up"
+          }
+        },
+        "required": [
+          "style"
+        ]
+      },
       "TextToImageAsset": {
         "description": "The TextToImageAsset lets you create a dynamic image from a text prompt.",
         "properties": {
@@ -3462,7 +3700,7 @@
             "description": "The text color using hexadecimal color notation.",
             "type": "string",
             "pattern": "^#[A-Fa-f0-9]{6}$",
-            "default": "#ffffff",
+            "default": "#000000",
             "example": "#ff0000"
           },
           "opacity": {
@@ -3495,6 +3733,13 @@
             "default": 0,
             "example": 2
           },
+          "wordSpacing": {
+            "description": "Additional spacing between words in pixels. A value of 0 uses the font's natural space width.",
+            "type": "number",
+            "minimum": 0,
+            "default": 0,
+            "example": 10
+          },
           "lineHeight": {
             "description": "The line height as a multiplier of the font size. Must be between 0 and 10.",
             "type": "number",

package/dist/schema.d.ts

@@ -583,7 +583,7 @@ export interface components {
             alias?: string;
         };
         /** @description The type of asset to display for the duration of the Clip, i.e. a video clip or an image. Choose from one of the available asset types below. */
-        Asset: components["schemas"]["VideoAsset"] | components["schemas"]["ImageAsset"] | components["schemas"]["TextAsset"] | components["schemas"]["RichTextAsset"] | components["schemas"]["AudioAsset"] | components["schemas"]["LumaAsset"] | components["schemas"]["CaptionAsset"] | components["schemas"]["HtmlAsset"] | components["schemas"]["TitleAsset"] | components["schemas"]["ShapeAsset"] | components["schemas"]["SvgAsset"] | components["schemas"]["TextToImageAsset"] | components["schemas"]["ImageToVideoAsset"] | components["schemas"]["TextToSpeechAsset"];
+        Asset: components["schemas"]["VideoAsset"] | components["schemas"]["ImageAsset"] | components["schemas"]["TextAsset"] | components["schemas"]["RichTextAsset"] | components["schemas"]["AudioAsset"] | components["schemas"]["LumaAsset"] | components["schemas"]["CaptionAsset"] | components["schemas"]["RichCaptionAsset"] | components["schemas"]["HtmlAsset"] | components["schemas"]["TitleAsset"] | components["schemas"]["ShapeAsset"] | components["schemas"]["SvgAsset"] | components["schemas"]["TextToImageAsset"] | components["schemas"]["ImageToVideoAsset"] | components["schemas"]["TextToSpeechAsset"];
         /** @description The VideoAsset is used to create video sequences from video files. The src must be a publicly accessible URL to a video resource such as an mp4 file. */
         VideoAsset: {
             /**
@@ -968,6 +968,150 @@ export interface components {
              */
             speed?: number;
         };
+        /**
+         * @description The RichCaptionAsset provides word-level caption animations with rich-text styling. It supports
+         *     karaoke-style highlighting, word-by-word animations, and advanced typography. Use with SRT/VTT
+         *     files or auto-transcription via aliases.
+         */
+        RichCaptionAsset: {
+            /**
+             * @description The type of asset - set to `rich-caption` for rich captions. (enum property replaced by openapi-typescript)
+             * @enum {string}
+             */
+            type: "rich-caption";
+            /**
+             * @description The URL to an SRT or VTT subtitles file, or an alias reference to auto-generate captions from an audio or video clip. For file URLs, the URL must be publicly accessible or include credentials. For auto-captioning, use the format `alias://clip-name` where clip-name is the alias of an audio, video, or text-to-speech clip. Mutually exclusive with `words`.
+             * @example alias://audio
+             */
+            src?: string;
+            /** @description Pre-provided word-level timing data. Use this instead of `src` when you have word timestamps from an external source. Mutually exclusive with `src`. */
+            words?: components["schemas"]["WordTiming"][];
+            /** @description Font styling properties for inactive words. */
+            font?: components["schemas"]["RichTextFont"];
+            /** @description Text style properties including spacing, line height, and transformations. */
+            style?: components["schemas"]["RichTextStyle"];
+            /** @description Text stroke (outline) properties for inactive words. */
+            stroke?: components["schemas"]["RichTextStroke"];
+            /** @description Text shadow properties. */
+            shadow?: components["schemas"]["RichTextShadow"];
+            /** @description Background styling properties for the caption bounding box. */
+            background?: components["schemas"]["RichTextBackground"];
+            /** @description Padding inside the caption bounding box. Can be a single number (applied to all sides) or an object with individual sides. */
+            padding?: number | components["schemas"]["RichTextAsset"]["padding"]["oneOf"]["1"];
+            /** @description Text alignment properties (horizontal and vertical). */
+            align?: components["schemas"]["RichTextAlignment"];
+            /** @description Styling properties for the active/highlighted word. These override the base styling when a word is being spoken. */
+            active?: components["schemas"]["RichCaptionActive"];
+            /** @description Word-level animation properties controlling how words are highlighted or revealed. */
+            wordAnimation?: components["schemas"]["RichCaptionWordAnimation"];
+            /**
+             * @description Vertical position of the caption on screen.
+             * @default bottom
+             * @example bottom
+             * @enum {string}
+             */
+            position: "top" | "center" | "bottom";
+            /**
+             * @description Maximum width of the caption as a ratio of the frame width. Must be between 0.1 and 1.
+             * @default 0.9
+             * @example 0.85
+             */
+            maxWidth: number;
+            /**
+             * @description Maximum number of lines to display at once. Must be between 1 and 10.
+             * @default 2
+             * @example 2
+             */
+            maxLines: number;
+        };
+        /** @description Word-level timing information for caption animation. */
+        WordTiming: {
+            /**
+             * @description The word text to display.
+             * @example Hello
+             */
+            text: string;
+            /**
+             * @description Start time of the word in milliseconds.
+             * @example 0
+             */
+            start: number;
+            /**
+             * @description End time of the word in milliseconds.
+             * @example 400
+             */
+            end: number;
+            /**
+             * @description Speech-to-text confidence score between 0 and 1.
+             * @example 0.98
+             */
+            confidence?: number;
+        };
+        /** @description Font properties for the active/highlighted word. */
+        RichCaptionActiveFont: {
+            /**
+             * @description The active word color using hexadecimal color notation.
+             * @default #ffff00
+             * @example #ffff00
+             */
+            color: string;
+            /**
+             * @description The background color behind the active word using hexadecimal color notation.
+             * @example #000000
+             */
+            background?: string;
+            /**
+             * @description The opacity of the active word where 1 is opaque and 0 is transparent.
+             * @default 1
+             * @example 1
+             */
+            opacity: number;
+        };
+        /** @description Styling properties for the active/highlighted word. */
+        RichCaptionActive: {
+            /** @description Font properties for the active word. */
+            font?: components["schemas"]["RichCaptionActiveFont"];
+            /** @description Stroke properties for the active word. */
+            stroke?: components["schemas"]["RichTextStroke"];
+            /**
+             * @description Scale multiplier for the active word. 1.0 is normal size, 1.2 is 20% larger.
+             * @default 1
+             * @example 1.2
+             */
+            scale: number;
+        };
+        /** @description Word-level animation properties for caption effects. */
+        RichCaptionWordAnimation: {
+            /**
+             * @description The animation style to apply to words: <ul>
+             *       <li>`karaoke` - Word-by-word color fill as spoken (shows all words, highlights active)</li>
+             *       <li>`highlight` - Word changes to active color when spoken (shows all words)</li>
+             *       <li>`pop` - Each word scales up when active</li>
+             *       <li>`fade` - Gradual opacity transition per word</li>
+             *       <li>`slide` - Words slide in from a direction</li>
+             *       <li>`bounce` - Spring animation on word appearance</li>
+             *       <li>`typewriter` - Words appear one by one and stay visible</li>
+             *       <li>`none` - No animation, all words visible immediately</li>
+             *     </ul>
+             * @default karaoke
+             * @example karaoke
+             * @enum {string}
+             */
+            style: "karaoke" | "highlight" | "pop" | "fade" | "slide" | "bounce" | "typewriter" | "none";
+            /**
+             * @description Animation speed multiplier. 1.0 is normal speed, 0.5 is half speed, 2.0 is double speed.
+             * @default 1
+             * @example 1
+             */
+            speed: number;
+            /**
+             * @description Direction for directional animations (slide). Only applicable when style is `slide`.
+             * @default up
+             * @example up
+             * @enum {string}
+             */
+            direction: "left" | "right" | "up" | "down";
+        };
         /** @description The TextToImageAsset lets you create a dynamic image from a text prompt. */
         TextToImageAsset: {
             /**
@@ -2102,7 +2246,7 @@ export interface components {
             weight: unknown;
             /**
              * @description The text color using hexadecimal color notation.
-             * @default #ffffff
+             * @default #000000
              * @example #ff0000
              */
             color: string;
@@ -2128,6 +2272,12 @@ export interface components {
              * @example 2
              */
             letterSpacing: number;
+            /**
+             * @description Additional spacing between words in pixels. A value of 0 uses the font's natural space width.
+             * @default 0
+             * @example 10
+             */
+            wordSpacing: number;
             /**
              * @description The line height as a multiplier of the font size. Must be between 0 and 10.
              * @default 1.2