@juspay/neurolink 8.25.0 → 8.26.0

package/CHANGELOG.md

@@ -1,3 +1,9 @@
+## [8.26.0](https://github.com/juspay/neurolink/compare/v8.25.0...v8.26.0) (2025-12-30)
+
+### Features
+
+- **(types):** Add video output types (VIDEO-GEN-001) ([1b1b5c2](https://github.com/juspay/neurolink/commit/1b1b5c23d0bdacb9d3120797b1f7984d7e0cc48c))
+
 ## [8.25.0](https://github.com/juspay/neurolink/compare/v8.24.0...v8.25.0) (2025-12-30)
 
 ### Features

package/dist/lib/types/content.d.ts

@@ -14,5 +14,5 @@
  * import type { MultimodalInput } from './types/multimodal.js';
  * ```
  */
-export type { TextContent, ImageContent, CSVContent, PDFContent, AudioContent, VideoContent, Content, ImageWithAltText, MultimodalInput, MultimodalMessage, VisionCapability, ProviderImageFormat, ProcessedImage, ProviderMultimodalPayload, } from "./multimodal.js";
+export type { TextContent, ImageContent, CSVContent, PDFContent, AudioContent, VideoContent, VideoOutputOptions, VideoGenerationResult, Content, ImageWithAltText, MultimodalInput, MultimodalMessage, VisionCapability, ProviderImageFormat, ProcessedImage, ProviderMultimodalPayload, } from "./multimodal.js";
 export { isTextContent, isImageContent, isCSVContent, isPDFContent, isAudioContent, isVideoContent, isMultimodalInput, } from "./multimodal.js";

package/dist/lib/types/generateTypes.d.ts

@@ -8,6 +8,7 @@ import type { MiddlewareFactoryOptions } from "./middlewareTypes.js";
 import type { JsonValue } from "./common.js";
 import type { Content, ImageWithAltText } from "./content.js";
 import type { TTSOptions, TTSResult } from "./ttsTypes.js";
+import type { VideoOutputOptions, VideoGenerationResult } from "./multimodal.js";
 /**
  * Generate function options type - Primary method for content generation
  * Supports multimodal content while maintaining backward compatibility
@@ -39,8 +40,41 @@ export type GenerateOptions = {
         files?: Array<Buffer | string>;
         content?: Content[];
     };
+    /**
+     * Output configuration options
+     *
+     * @example Text output (default)
+     * ```typescript
+     * output: { format: "text" }
+     * ```
+     *
+     * @example Video generation with Veo 3.1
+     * ```typescript
+     * output: {
+     *   mode: "video",
+     *   video: {
+     *     resolution: "1080p",
+     *     length: 8,
+     *     aspectRatio: "16:9",
+     *     audio: true
+     *   }
+     * }
+     * ```
+     */
     output?: {
+        /** Output format for text generation */
         format?: "text" | "structured" | "json";
+        /**
+         * Output mode - determines the type of content generated
+         * - "text": Standard text generation (default)
+         * - "video": Video generation using models like Veo 3.1
+         */
+        mode?: "text" | "video";
+        /**
+         * Video generation configuration (used when mode is "video")
+         * Requires an input image and text prompt
+         */
+        video?: VideoOutputOptions;
     };
     csvOptions?: {
         maxRows?: number;
@@ -207,6 +241,29 @@ export type GenerateResult = {
      * ```
      */
     audio?: TTSResult;
+    /**
+     * Video generation result
+     *
+     * Contains the generated video buffer and metadata when video mode is enabled.
+     * Present when `output.mode` is set to "video" in GenerateOptions.
+     *
+     * @example Accessing generated video
+     * ```typescript
+     * const result = await neurolink.generate({
+     *   input: { text: "Product showcase", images: [imageBuffer] },
+     *   provider: "vertex",
+     *   model: "veo-3.1",
+     *   output: { mode: "video", video: { resolution: "1080p" } }
+     * });
+     *
+     * if (result.video) {
+     *   fs.writeFileSync('output.mp4', result.video.data);
+     *   console.log(`Duration: ${result.video.metadata?.duration}s`);
+     *   console.log(`Dimensions: ${result.video.metadata?.dimensions?.width}x${result.video.metadata?.dimensions?.height}`);
+     * }
+     * ```
+     */
+    video?: VideoGenerationResult;
     provider?: string;
     model?: string;
     usage?: TokenUsage;

package/dist/lib/types/index.js

@@ -33,7 +33,7 @@ export * from "./utilities.js";
 export * from "./middlewareTypes.js";
 // File detection and processing types
 export * from "./fileTypes.js";
-// Content types for multimodal support
+// Content types for multimodal support (includes multimodal re-exports for backward compatibility)
 export * from "./content.js";
 // TTS (Text-to-Speech) types
 export * from "./ttsTypes.js";

package/dist/lib/types/multimodal.d.ts

@@ -124,6 +124,85 @@ export type AudioContent = {
         language?: string;
     };
 };
+/**
+ * Video output configuration options for video generation
+ *
+ * Used with `output.video` in GenerateOptions when `output.mode` is "video".
+ * Controls resolution, duration, aspect ratio, and audio settings for generated videos.
+ *
+ * @example
+ * ```typescript
+ * const videoOptions: VideoOutputOptions = {
+ *   resolution: "1080p",
+ *   length: 8,
+ *   aspectRatio: "16:9",
+ *   audio: true
+ * };
+ * ```
+ */
+export type VideoOutputOptions = {
+    /** Output resolution - "720p" (1280x720) or "1080p" (1920x1080) */
+    resolution?: "720p" | "1080p";
+    /** Video duration in seconds (4, 6, or 8 seconds supported) */
+    length?: 4 | 6 | 8;
+    /** Aspect ratio - "9:16" for portrait or "16:9" for landscape */
+    aspectRatio?: "9:16" | "16:9";
+    /** Enable audio generation (default: true) */
+    audio?: boolean;
+};
+/**
+ * Result type for generated video content
+ *
+ * Returned in `GenerateResult.video` when video generation is successful.
+ * Contains the raw video buffer and associated metadata.
+ *
+ * @example
+ * ```typescript
+ * const result = await neurolink.generate({
+ *   input: { text: "Product showcase", images: [imageBuffer] },
+ *   provider: "vertex",
+ *   model: "veo-3.1",
+ *   output: { mode: "video" }
+ * });
+ *
+ * if (result.video) {
+ *   writeFileSync("output.mp4", result.video.data);
+ *   console.log(`Duration: ${result.video.metadata?.duration}s`);
+ * }
+ * ```
+ */
+export type VideoGenerationResult = {
+    /** Raw video data as Buffer */
+    data: Buffer;
+    /** Video media type */
+    mediaType: "video/mp4" | "video/webm";
+    /** Video metadata */
+    metadata?: {
+        /** Original filename if applicable */
+        filename?: string;
+        /** Video duration in seconds */
+        duration?: number;
+        /** Video dimensions */
+        dimensions?: {
+            width: number;
+            height: number;
+        };
+        /** Frame rate in fps */
+        frameRate?: number;
+        /** Video codec used */
+        codec?: string;
+        /** Model used for generation */
+        model?: string;
+        /** Provider used for generation */
+        provider?: string;
+        /** Aspect ratio of the video */
+        aspectRatio?: string;
+        /** Whether audio was enabled during generation */
+        audioEnabled?: boolean;
+        /** Processing time in milliseconds */
+        processingTime?: number;
+    };
+};
 /**
  * Video content type for multimodal messages
  *

package/dist/types/content.d.ts

@@ -14,5 +14,5 @@
  * import type { MultimodalInput } from './types/multimodal.js';
  * ```
  */
-export type { TextContent, ImageContent, CSVContent, PDFContent, AudioContent, VideoContent, Content, ImageWithAltText, MultimodalInput, MultimodalMessage, VisionCapability, ProviderImageFormat, ProcessedImage, ProviderMultimodalPayload, } from "./multimodal.js";
+export type { TextContent, ImageContent, CSVContent, PDFContent, AudioContent, VideoContent, VideoOutputOptions, VideoGenerationResult, Content, ImageWithAltText, MultimodalInput, MultimodalMessage, VisionCapability, ProviderImageFormat, ProcessedImage, ProviderMultimodalPayload, } from "./multimodal.js";
 export { isTextContent, isImageContent, isCSVContent, isPDFContent, isAudioContent, isVideoContent, isMultimodalInput, } from "./multimodal.js";

package/dist/types/generateTypes.d.ts

@@ -8,6 +8,7 @@ import type { MiddlewareFactoryOptions } from "./middlewareTypes.js";
 import type { JsonValue } from "./common.js";
 import type { Content, ImageWithAltText } from "./content.js";
 import type { TTSOptions, TTSResult } from "./ttsTypes.js";
+import type { VideoOutputOptions, VideoGenerationResult } from "./multimodal.js";
 /**
  * Generate function options type - Primary method for content generation
  * Supports multimodal content while maintaining backward compatibility
@@ -39,8 +40,41 @@ export type GenerateOptions = {
         files?: Array<Buffer | string>;
         content?: Content[];
     };
+    /**
+     * Output configuration options
+     *
+     * @example Text output (default)
+     * ```typescript
+     * output: { format: "text" }
+     * ```
+     *
+     * @example Video generation with Veo 3.1
+     * ```typescript
+     * output: {
+     *   mode: "video",
+     *   video: {
+     *     resolution: "1080p",
+     *     length: 8,
+     *     aspectRatio: "16:9",
+     *     audio: true
+     *   }
+     * }
+     * ```
+     */
     output?: {
+        /** Output format for text generation */
         format?: "text" | "structured" | "json";
+        /**
+         * Output mode - determines the type of content generated
+         * - "text": Standard text generation (default)
+         * - "video": Video generation using models like Veo 3.1
+         */
+        mode?: "text" | "video";
+        /**
+         * Video generation configuration (used when mode is "video")
+         * Requires an input image and text prompt
+         */
+        video?: VideoOutputOptions;
     };
     csvOptions?: {
         maxRows?: number;
@@ -207,6 +241,29 @@ export type GenerateResult = {
      * ```
      */
     audio?: TTSResult;
+    /**
+     * Video generation result
+     *
+     * Contains the generated video buffer and metadata when video mode is enabled.
+     * Present when `output.mode` is set to "video" in GenerateOptions.
+     *
+     * @example Accessing generated video
+     * ```typescript
+     * const result = await neurolink.generate({
+     *   input: { text: "Product showcase", images: [imageBuffer] },
+     *   provider: "vertex",
+     *   model: "veo-3.1",
+     *   output: { mode: "video", video: { resolution: "1080p" } }
+     * });
+     *
+     * if (result.video) {
+     *   fs.writeFileSync('output.mp4', result.video.data);
+     *   console.log(`Duration: ${result.video.metadata?.duration}s`);
+     *   console.log(`Dimensions: ${result.video.metadata?.dimensions?.width}x${result.video.metadata?.dimensions?.height}`);
+     * }
+     * ```
+     */
+    video?: VideoGenerationResult;
     provider?: string;
     model?: string;
     usage?: TokenUsage;

package/dist/types/index.js

@@ -33,7 +33,7 @@ export * from "./utilities.js";
 export * from "./middlewareTypes.js";
 // File detection and processing types
 export * from "./fileTypes.js";
-// Content types for multimodal support
+// Content types for multimodal support (includes multimodal re-exports for backward compatibility)
 export * from "./content.js";
 // TTS (Text-to-Speech) types
 export * from "./ttsTypes.js";

package/dist/types/multimodal.d.ts

@@ -124,6 +124,85 @@ export type AudioContent = {
         language?: string;
     };
 };
+/**
+ * Video output configuration options for video generation
+ *
+ * Used with `output.video` in GenerateOptions when `output.mode` is "video".
+ * Controls resolution, duration, aspect ratio, and audio settings for generated videos.
+ *
+ * @example
+ * ```typescript
+ * const videoOptions: VideoOutputOptions = {
+ *   resolution: "1080p",
+ *   length: 8,
+ *   aspectRatio: "16:9",
+ *   audio: true
+ * };
+ * ```
+ */
+export type VideoOutputOptions = {
+    /** Output resolution - "720p" (1280x720) or "1080p" (1920x1080) */
+    resolution?: "720p" | "1080p";
+    /** Video duration in seconds (4, 6, or 8 seconds supported) */
+    length?: 4 | 6 | 8;
+    /** Aspect ratio - "9:16" for portrait or "16:9" for landscape */
+    aspectRatio?: "9:16" | "16:9";
+    /** Enable audio generation (default: true) */
+    audio?: boolean;
+};
+/**
+ * Result type for generated video content
+ *
+ * Returned in `GenerateResult.video` when video generation is successful.
+ * Contains the raw video buffer and associated metadata.
+ *
+ * @example
+ * ```typescript
+ * const result = await neurolink.generate({
+ *   input: { text: "Product showcase", images: [imageBuffer] },
+ *   provider: "vertex",
+ *   model: "veo-3.1",
+ *   output: { mode: "video" }
+ * });
+ *
+ * if (result.video) {
+ *   writeFileSync("output.mp4", result.video.data);
+ *   console.log(`Duration: ${result.video.metadata?.duration}s`);
+ * }
+ * ```
+ */
+export type VideoGenerationResult = {
+    /** Raw video data as Buffer */
+    data: Buffer;
+    /** Video media type */
+    mediaType: "video/mp4" | "video/webm";
+    /** Video metadata */
+    metadata?: {
+        /** Original filename if applicable */
+        filename?: string;
+        /** Video duration in seconds */
+        duration?: number;
+        /** Video dimensions */
+        dimensions?: {
+            width: number;
+            height: number;
+        };
+        /** Frame rate in fps */
+        frameRate?: number;
+        /** Video codec used */
+        codec?: string;
+        /** Model used for generation */
+        model?: string;
+        /** Provider used for generation */
+        provider?: string;
+        /** Aspect ratio of the video */
+        aspectRatio?: string;
+        /** Whether audio was enabled during generation */
+        audioEnabled?: boolean;
+        /** Processing time in milliseconds */
+        processingTime?: number;
+    };
+};
 /**
  * Video content type for multimodal messages
  *

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@juspay/neurolink",
-  "version": "8.25.0",
+  "version": "8.26.0",
   "description": "Universal AI Development Platform with working MCP integration, multi-provider support, and professional CLI. Built-in tools operational, 58+ external MCP servers discoverable. Connect to filesystem, GitHub, database operations, and more. Build, test, and deploy AI applications with 13 providers: OpenAI, Anthropic, Google AI, AWS Bedrock, Azure, Hugging Face, Ollama, and Mistral AI.",
   "author": {
     "name": "Juspay Technologies",