ugcinc 4.21.0 → 4.22.0

package/README.md

@@ -362,3 +362,21 @@ than caching by URL. Results include source SHA-256, encoded/display dimensions,
 rotation, time base, source starting PTS, decoded frame count and an owned manifest.
 Video URLs must be public HTTPS sources. Limits: 100 MB, 30 minutes, 4096 pixels per
 encoded dimension, 120,000 decoded frames. Unsupported/malformed media fails explicitly.
+
+### Image and video OCR
+
+Quick reference: `client.media.readImageText({url})`, `client.media.readVideoText({url, mode, range?, intervalMs?})`; agent tools `read_image_text` and `read_video_text`. Both use the authenticated analysis job/status flow above.
+
+```ts
+const imageText = await client.media.readImageText({url: imageUrl});
+const sampledText = await client.media.readVideoText({url: videoUrl, mode: 'fast', intervalMs: 1000});
+const everyFrame = await client.media.readVideoText({url: videoUrl, mode: 'frame_scan', range: {startMs: 0, endMs: 5000}});
+```
+
+`POST /media/analysis/read-image-text` accepts an HTTPS image URL. Results contain `regions` (raw recognized text, four-point polygon, enclosing box, model confidence, readable/unreadable status), inferred `lines` with region IDs and reading order, source dimensions/hash, model details, `previewUrl` and `manifestUrl`. Coordinates are pixels after EXIF orientation; transparent pixels are composited on white. English recognition only; no guaranteed reading order for columns or inverted text. Low-confidence candidates retain `rawText` but return `text: null`. Undetected text cannot be marked unreadable, and empty output does not prove absence. Images must be static, at most 4096 pixels per axis /16 megapixels, and at most 100 MiB.
+
+`POST /media/analysis/read-video-text` accepts a video URL, `mode` (`fast` default or `frame_scan`), optional `{startMs,endMs}` range and optional `intervalMs` (fast only, default1000, minimum100). Range end is exclusive; range defaults to the whole clip. A request may cover at most120 seconds and inspect at most240 frames; split longer frame scans into ranges. Invalid/excessive requests fail explicitly, never silently truncate. Times are relative to the first displayed frame; original `sourcePts` and time base are retained. The frame displayed at a partial range's start is included, so its source timestamp can precede `startMs`.
+
+Results include per-frame regions/lines, up to eight annotated frame previews, heuristic text `tracks` with observed boxes, and `coverage.inspected` plus `coverage.uninspected`. `coverage.complete` means all displayed frames within the range were inspected, not that OCR found every word. A track's `firstObservedMs` / `lastObservedEndMs` bounds observations; it does not prove uninterrupted visibility between sampled frames. Fast mode can miss brief text entirely. Fully scanned recognized single-frame text retains its decoded frame interval. Recognition scores are not calibrated probabilities. Track identity, scene-change rejection and line grouping are estimates; use individual observations and polygons for evidence.
+
+Both methods return `ApiResponse<MediaAnalysisJob>`, waiting through up to180 two-second status polls. A pending/processing response retains `jobId`; resume with `getMediaAnalysis({jobId})`. Job results include model/runtime versions and SHA-256 checksums. These CPU jobs share the existing bounded analysis queue. A failed job does not return partial OCR as complete.

package/dist/automations/nodes/index.d.ts

@@ -340,7 +340,7 @@ export declare const nodeDefinitions: {
         selectionMode: null;
         outputType: "video" | "image";
         inputs: {
-            type: "number" | "boolean" | "object" | "video" | "image" | "audio" | "text";
+            type: "number" | "boolean" | "object" | "video" | "image" | "text" | "audio";
             id: string;
             isArray: boolean;
             required: boolean;

package/dist/automations/nodes/remotion-composition.d.ts

@@ -11,7 +11,7 @@ declare const defaults: {
     selectionMode: null;
     outputType: "video" | "image";
     inputs: {
-        type: "number" | "boolean" | "object" | "video" | "image" | "audio" | "text";
+        type: "number" | "boolean" | "object" | "video" | "image" | "text" | "audio";
         id: string;
         isArray: boolean;
         required: boolean;
@@ -28,7 +28,7 @@ declare const _default: import("./types").NodeDefinition<"remotion-composition",
     selectionMode: null;
     outputType: "video" | "image";
     inputs: {
-        type: "number" | "boolean" | "object" | "video" | "image" | "audio" | "text";
+        type: "number" | "boolean" | "object" | "video" | "image" | "text" | "audio";
         id: string;
         isArray: boolean;
         required: boolean;

package/dist/index.d.ts

@@ -86,5 +86,5 @@ export type { SuccessResponse, ErrorResponse, ApiResponse, } from './types';
 export type { CropBoundary, CropAxisConfig, DynamicCropConfig, BorderRadiusConfig, VerticalAnchor, HorizontalAnchor, HorizontalSelfAnchor, VerticalSelfAnchor, RelativePositionConfigX, RelativePositionConfigY, } from './render/types';
 export type { PublicPostFailureCode, PublicPostRecovery, PublicPostNextAction, PublicPostFailure } from './post-failure';
 export type { ListProfilePostsParams, ListProfilePostsResult, DownloadSocialPostParams, DownloadSocialPostResult, SocialReferencePost, SocialReferenceAsset } from './social-acquisition';
-export type { ExtractFramesParams, DetectScenesParams, FramesResult, ScenesResult, MediaAnalysisResult, MediaAnalysisJob } from "./media-analysis";
-export { extractFramesSchema, detectScenesSchema, mediaAnalysisStatusSchema, mediaAnalysisResultSchema } from "./media-analysis";
+export type { ReadImageTextParams, ReadVideoTextParams, ImageTextResult, VideoTextResult, ExtractFramesParams, DetectScenesParams, FramesResult, ScenesResult, MediaAnalysisResult, MediaAnalysisJob } from "./media-analysis";
+export { readImageTextSchema, readVideoTextSchema, imageTextResultSchema, videoTextResultSchema, extractFramesSchema, detectScenesSchema, mediaAnalysisStatusSchema, mediaAnalysisResultSchema } from "./media-analysis";

package/dist/index.js

@@ -7,7 +7,7 @@
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.hasMissingTriggerError = exports.getPortErrorsForNode = exports.getErrorNodeIds = exports.validateWorkflow = exports.getCapturedNodes = exports.getNodesDownstreamOfSet = exports.getDownstreamNodes = exports.checkCrossContextViolation = exports.getForEachContext = exports.getConnectedSource = exports.cleanupStaleConnections = exports.removeNodeConnections = exports.removeConnection = exports.addConnection = exports.deriveConnections = exports.createNode = exports.getOutputSchema = exports.getNodeByType = exports.getAllNodes = exports.getInputPreviewValue = exports.computeAllNodePortsWithPreviews = exports.computeAllNodePorts = exports.computePortsWithPreviews = exports.computePortsForNode = exports.areTypesCompatible = exports.parseRemotionPropsJson = exports.REMOTION_COMPOSITION_IMPORTS = exports.remotionCompositionPortSchema = exports.remotionCompositionNodeSchema = exports.remotionCompositionSchema = exports.submitIMessageDmRenderJob = exports.submitInstagramDmRenderJob = exports.submitAutoCaptionRenderJob = exports.submitRemotionCompositionRenderJob = exports.submitScreenshotAnimationRenderJob = exports.submitSceneSplitJob = exports.submitDeduplicationJob = exports.getRenderJobStatus = exports.submitVideoRenderJob = exports.submitImageRenderJob = exports.BillingClient = exports.CommentsClient = exports.MediaClient = exports.AutomationsClient = exports.OrganizationClient = exports.StatsClient = exports.PostsClient = exports.TasksClient = exports.AccountsClient = exports.UGCClient = void 0;
 exports.parseOpenAPIOutputPath = exports.parseOpenAPIInputs = exports.mapOpenAPIType = exports.nodeConfigToCaptionStyle = exports.HttpMethods = exports.prepareImageComposerInput = exports.substituteVariables = exports.processTemplate = exports.extractTemplateVariables = exports.PortIdSchema = exports.normalizeToPortId = exports.portIdToTitle = exports.isValidPortId = exports.portId = exports.selectFromPool = exports.getModelDurations = exports.getModelAspectRatios = exports.ALL_VIDEO_MODELS = exports.getAvailableInputModes = exports.hasReferenceVariant = exports.getReferenceModelId = exports.hasFirstLastFrameVariant = exports.getFirstLastFrameModelId = exports.hasImageToVideoVariant = exports.getImageToVideoModelId = exports.isImageToVideoModel = exports.IMAGE_ASPECT_RATIOS = exports.ALL_IMAGE_MODELS = exports.getEditModelId = exports.isEditModel = exports.getCapturedSourceNodeTypes = exports.getFlowControlNodeTypes = exports.getAllNodeDefinitions = exports.getNodeDefinition = exports.isPortType = exports.formatPortType = exports.isAsyncExecutor = exports.internalNodeTypes = exports.nodeDefinitions = exports.extractWorkflowConfig = exports.generateNodeName = exports.shuffleNodePreview = exports.getPreviewValue = exports.removePreviewForConnection = exports.updatePreviewMapForConnection = exports.computePreviewMap = exports.computeAllNodePreviews = exports.resolveNodePreview = exports.getWorkflowOutputSchema = exports.hasMissingTerminalError = void 0;
-exports.mediaAnalysisResultSchema = exports.mediaAnalysisStatusSchema = exports.detectScenesSchema = exports.extractFramesSchema = exports.prepareVideoComposerInput = exports.formatDateTag = exports.outputFieldsToZod = exports.outputFieldToZod = exports.LLMProviders = exports.applyLogicOperator = exports.IfLogicOperators = exports.resolvePath = exports.indexExpressionToString = exports.indexExpressionToIndexes = exports.resolveUnknownPath = exports.getOutputTypeFromCategory = void 0;
+exports.mediaAnalysisResultSchema = exports.mediaAnalysisStatusSchema = exports.detectScenesSchema = exports.extractFramesSchema = exports.videoTextResultSchema = exports.imageTextResultSchema = exports.readVideoTextSchema = exports.readImageTextSchema = exports.prepareVideoComposerInput = exports.formatDateTag = exports.outputFieldsToZod = exports.outputFieldToZod = exports.LLMProviders = exports.applyLogicOperator = exports.IfLogicOperators = exports.resolvePath = exports.indexExpressionToString = exports.indexExpressionToIndexes = exports.resolveUnknownPath = exports.getOutputTypeFromCategory = void 0;
 // =============================================================================
 // Client Exports
 // =============================================================================
@@ -175,6 +175,10 @@ Object.defineProperty(exports, "formatDateTag", { enumerable: true, get: functio
 var video_composer_1 = require("./automations/nodes/video-composer");
 Object.defineProperty(exports, "prepareVideoComposerInput", { enumerable: true, get: function () { return video_composer_1.prepareVideoComposerInput; } });
 var media_analysis_1 = require("./media-analysis");
+Object.defineProperty(exports, "readImageTextSchema", { enumerable: true, get: function () { return media_analysis_1.readImageTextSchema; } });
+Object.defineProperty(exports, "readVideoTextSchema", { enumerable: true, get: function () { return media_analysis_1.readVideoTextSchema; } });
+Object.defineProperty(exports, "imageTextResultSchema", { enumerable: true, get: function () { return media_analysis_1.imageTextResultSchema; } });
+Object.defineProperty(exports, "videoTextResultSchema", { enumerable: true, get: function () { return media_analysis_1.videoTextResultSchema; } });
 Object.defineProperty(exports, "extractFramesSchema", { enumerable: true, get: function () { return media_analysis_1.extractFramesSchema; } });
 Object.defineProperty(exports, "detectScenesSchema", { enumerable: true, get: function () { return media_analysis_1.detectScenesSchema; } });
 Object.defineProperty(exports, "mediaAnalysisStatusSchema", { enumerable: true, get: function () { return media_analysis_1.mediaAnalysisStatusSchema; } });