Class Index

These are all the API classes. See all API packages.

A B C D E F G H I J L M N O P R S T U V W

A

`AppSearchVectorStore`	A vector store implementation using Android system-level AppSearch storage.
`AudioChunk`	Incremental mono PCM audio chunk emitted by `TextToSpeech.synthesizeStream`.
`AudioClassifier`	Performs audio classification on audio clips or audio stream.
`AudioClassifier.AudioClassifierOptions`	Options for setting up and `AudioClassifier`.
`AudioClassifier.AudioClassifierOptions.Builder`	Builder for `AudioClassifierOptions`.
`AudioClassifierResult`	Represents the classification results generated by `AudioClassifier`.
`AudioData`	Defines a ring buffer and some utility functions to prepare the input audio samples.
`AudioData.AudioDataFormat`	Wraps a few constants describing the format of the incoming audio samples, namely number of channels and the sample rate.
`AudioData.AudioDataFormat.Builder`	Builder for `AudioDataFormat`
`AudioPart`	Represents an audio part of a multi-modal content block.
`AudioResult`	Self-contained mono PCM audio buffer returned by `TextToSpeech.synthesize`.
`AudioTranscriber`	Performs streaming and non-streaming speech-to-text transcription on mono PCM float audio.
`AudioTranscriber.AudioTranscriberOptions`	Options for setting up an `AudioTranscriber`.
`AudioTranscriber.AudioTranscriberOptions.Builder`	Builder for `AudioTranscriberOptions`.
`AudioTranscriber.ModelArchitecture`	Model architecture backend family for `AudioTranscriber`.
`AudioTranscriberResult`	Represents the transcription results generated by `AudioTranscriber`.
`AudioTranscriberResult.Segment`	Represents a single transcribed segment emitted by `AudioTranscriber`.

B

`BaseAudioTaskApi`	The base class of MediaPipe audio tasks.
`BaseOptions`	Options to configure MediaPipe Tasks in general.
`BaseOptions.Builder`	Builder for `BaseOptions`.
`BaseOptions.DelegateOptions`	Advanced config options for the used delegate.
`BaseOptions.DelegateOptions.CpuOptions`	Options for CPU.
`BaseOptions.DelegateOptions.CpuOptions.Builder`	Builder for `CpuOptions`.
`BaseOptions.DelegateOptions.GpuOptions`	Options for GPU.
`BaseOptions.DelegateOptions.GpuOptions.Builder`	Builder for `GpuOptions`.
`BaseOptions.DelegateOptions.NpuOptions`	Options for NPU.
`BaseOptions.DelegateOptions.NpuOptions.Builder`	Builder for `NpuOptions`.
`BaseOptionsUtils`	Utility for `BaseOptions`.
`BaseVisionTaskApi`	The base class of MediaPipe vision tasks.
`BitmapExtractor`	Utility for extracting `android.graphics.Bitmap` from `MPImage`.
`BitmapImageBuilder`	Builds `MPImage` from `android.graphics.Bitmap`.
`BooleanQuestion`	Evaluates a natural-language boolean predicate as `true` or `false` with a calibrated probability and confidence score.
`BooleanResult`	Calibrated result of evaluating a `BooleanQuestion`.
`ByteBufferExtractor`	Utility for extracting `ByteBuffer` from `MPImage`.
`ByteBufferImageBuilder`	Builds a `MPImage` from a `ByteBuffer`.

C

`Category`	Category is a util class, that contains a category name, its display name, a float value as score, and the index of the label in the corresponding label file.
`ChoiceQuestion`	Evaluates a mutually exclusive categorical choice menu and returns a calibrated probability distribution over `choices`.
`ChoiceResult`	Calibrated result of evaluating a `ChoiceQuestion`.
`ClassificationResult`	Represents the classification results of a model.
`Classifications`	Represents the list of classification for a given classifier head.
`ClassifierOptions`	Classifier options shared across MediaPipe Java classification tasks.
`ClassifierOptions.Builder`	Builder for `ClassifierOptions`.
`ColumnConfig`	SQLite table column configuration.
`ColumnConfig.KeyType`	The type of key this column is.
`Connection`	Value class representing a landmark connection.
`CosineSimilarity`	Utility class for computing cosine similarity between `Embedding` objects.

D

`DecisionContext`	Perceptual input context for multimodal or text-only decision evaluation.
`DecisionMaker`	MediaPipe Decision Task API for Android / Kotlin.
`DecisionMakerDelegate`	Hardware delegate selection for running MediaPipe Decision inference.
`DecisionMakerOptions`	Configuration options for initializing a `DecisionMaker` task instance.
`DecisionMakerOptions.Builder`	Builder for `DecisionMakerOptions`.
`DecisionMakerOptions.Companion`
`DecisionQuestion`	Sealed hierarchy of structured questions evaluated by Decision.
`DefaultTextChunker`	A default text chunking implementation using native C++ word-based chunking with overlap or character sliding window.
`DefaultTextChunker.ChunkingMode`	Mode for text chunking.
`Delegate`	MediaPipe Tasks delegate.
`Detection`	Represents one detected object in the results of com.google.mediapipe.tasks.version.objectdetector.ObjectDetector.

E

`Embedding`	Represents the embedding for a given embedder head.
`EmbeddingProvider`	Interface for generating embeddings across different modalities using content parts.
`EmbeddingResult`	Represents the embedding results of a model.
`ErrorListener`	Interface for the customizable MediaPipe task error listener.

F

`FaceDetector`	Performs face detection on images.
`FaceDetector.FaceDetectorOptions`	Options for setting up a `FaceDetector`.
`FaceDetector.FaceDetectorOptions.Builder`	Builder for `FaceDetectorOptions`.
`FaceDetectorResult`	Represents the detection results generated by `FaceDetector`.
`FaceLandmarker`	Performs face landmarks detection on images.
`FaceLandmarker.FaceLandmarkerOptions`	Options for setting up an `FaceLandmarker`.
`FaceLandmarker.FaceLandmarkerOptions.Builder`	Builder for `FaceLandmarkerOptions`.
`FaceLandmarkerResult`	Represents the face landmarks detection results generated by `FaceLandmarker`.

G

`GestureRecognizer`	Performs gesture recognition on images.
`GestureRecognizer.GestureRecognizerOptions`	Options for setting up an `GestureRecognizer`.
`GestureRecognizer.GestureRecognizerOptions.Builder`	Builder for `GestureRecognizerOptions`.
`GestureRecognizerResult`	Represents the gesture recognition results generated by `GestureRecognizer`.

H

`HandLandmark`	The 21 hand landmarks.
`HandLandmark.HandLandmarkType`	Represents a hand landmark type.
`HandLandmarker`	Performs hand landmarks detection on images.
`HandLandmarker.HandLandmarkerOptions`	Options for setting up an `HandLandmarker`.
`HandLandmarker.HandLandmarkerOptions.Builder`	Builder for `HandLandmarkerOptions`.
`HandLandmarkerResult`	Represents the hand landmarks deection results generated by `HandLandmarker`.
`HolisticLandmarker`	Performs holistic landmarks detection on images.
`HolisticLandmarker.HolisticLandmarkerOptions`	Options for setting up an `HolisticLandmarker`.
`HolisticLandmarker.HolisticLandmarkerOptions.Builder`	Builder for `HolisticLandmarkerOptions`.
`HolisticLandmarkerResult`	Represents the holistic landmarks detection results generated by `HolisticLandmarker`.

I

`ImageClassifier`	Performs classification on images.
`ImageClassifier.ImageClassifierOptions`	Options for setting up and `ImageClassifier`.
`ImageClassifier.ImageClassifierOptions.Builder`	Builder for `ImageClassifierOptions`.
`ImageClassifierResult`	Represents the classification results generated by `ImageClassifier`.
`ImageDecoder`	Stateless utility class managing the decoding of images from a Uri.
`ImageEmbedder`	Performs embedding extraction on images.
`ImageEmbedder.ImageEmbedderOptions`	Options for setting up and `ImageEmbedder`.
`ImageEmbedder.ImageEmbedderOptions.Builder`	Builder for `ImageEmbedderOptions`.
`ImageEmbedderExecutor`	Executor interface to isolate and branch Image Embedder executions.
`ImageEmbedderLiteRtLmExecutorImpl`	Helper implementation class for LiteRT-LM Image Embedder integration.
`ImageEmbedderResult`	Represents the embedding results generated by `ImageEmbedder`.
`ImagePart`	Represents an image part of a multi-modal content block.
`ImageProcessingOptions`	Options for image processing.
`ImageProcessingOptions.Builder`	Builder for `ImageProcessingOptions`.
`ImageSegmenter`	Performs image segmentation on images.
`ImageSegmenter.ImageSegmenterOptions`	Options for setting up an `ImageSegmenter`.
`ImageSegmenter.ImageSegmenterOptions.Builder`	Builder for `ImageSegmenterOptions`.
`ImageSegmenter.SegmentationOptions`	Options for configuring runtime behavior of `ImageSegmenter`.
`ImageSegmenter.SegmentationOptions.Builder`	Builder for `SegmentationOptions`
`ImageSegmenterResult`	Represents the segmentation results generated by `ImageSegmenter`.
`InteractiveSegmenter`	Performs interactive segmentation on images in two steps:
`InteractiveSegmenterLegacy`	Performs interactive segmentation on images.
`InteractiveSegmenterLegacy.InteractiveSegmenterLegacyOptions`	Options for setting up an `InteractiveSegmenterLegacy`.
`InteractiveSegmenterLegacy.InteractiveSegmenterLegacyOptions.Builder`	Builder for `InteractiveSegmenterLegacyOptions`.
`InteractiveSegmenterLegacy.RegionOfInterest`	The Region-Of-Interest (ROI) to interact with.
`InteractiveSegmenterOptions`	Options for setting up an `InteractiveSegmenter`.
`InteractiveSegmenterOptions.Builder`	Builder for `InteractiveSegmenterOptions`.

J

`JniConfig`	Build-time configuration for upstream MediaPipe Tasks JNI library names.
`JniConfigContract`	Contract interface defining runtime JNI library getters for MediaPipe Tasks.

L

`Landmark`	Landmark represents a point in 3D space with x, y, z coordinates.
`LanguageDetector`	Predicts the language of an input text.
`LanguageDetector.LanguageDetectorOptions`	Options for setting up a `LanguageDetector`.
`LanguageDetector.LanguageDetectorOptions.Builder`	Builder for `LanguageDetectorOptions`.
`LanguageDetectorResult`	Represents the prediction results generated by `LanguageDetector`.
`LanguagePrediction`	A language code and its probability.

M

`MPImage`	The wrapper class for image objects.
`MPImage.MPImageFormat`	Specifies the image format of an image.
`MPImage.StorageType`	Specifies the image container type.
`MPImageConsumer`	Lightweight abstraction for an object that can receive `MPImage`
`MPImageProducer`	Lightweight abstraction for an object that produce `MPImage`
`MPImageProperties`	Groups a set of properties to describe how an image is stored.
`MediaImageBuilder`	Builds `MPImage` from `android.media.Image`.
`MediaImageExtractor`	Utility for extracting `android.media.Image` from `MPImage`.
`MemoryRecordConverter`	Utility class for converting between RetrievalRecord and MemoryRecord protobuf.

N

`NormalizedKeypoint`	Normalized keypoint represents a point in 2D space with x, y coordinates. x and y are normalized to [0.0, 1.0] by the image width and height respectively.
`NormalizedLandmark`	Normalized Landmark represents a point in 3D space with x, y, z coordinates. x and y are normalized to [0.0, 1.0] by the image width and height respectively. z represents the landmark depth, and the smaller the value the closer the landmark is to the camera.

O

`ObjectDetectionResult`	This class is deprecated. Use `ObjectDetectorResult` instead.
`ObjectDetector`	Performs object detection on images.
`ObjectDetector.ObjectDetectorOptions`	Options for setting up an `ObjectDetector`.
`ObjectDetector.ObjectDetectorOptions.Builder`	Builder for `ObjectDetectorOptions`.
`ObjectDetectorResult`	Represents the detection results generated by `ObjectDetector`.
`OutputHandler`	Base class for handling MediaPipe task graph outputs.
`OutputHandler.OutputPacketConverter`	Interface for converting MediaPipe graph output `Packet`s to task result object and task input object.
`OutputHandler.ProgressListener`	Interface for the customizable MediaPipe task result listener that receives partial task updates until it is invoked with `done` set to `true`.
`OutputHandler.PureResultListener`	Interface for the customizable MediaPipe task result listener that can only retrieve task result objects.
`OutputHandler.ResultListener`	Interface for the customizable MediaPipe task result listener that can retrieve both task result objects and the corresponding input data.
`OutputHandler.ValueListener`	Interface for the customizable MediaPipe task result listener that only receives a task's output value.

P

`Part`	Represents a part of a multi-modal content block.
`PoseLandmarker`	Performs pose landmarks detection on images.
`PoseLandmarker.PoseLandmarkerOptions`	Options for setting up an `PoseLandmarker`.
`PoseLandmarker.PoseLandmarkerOptions.Builder`	Builder for `PoseLandmarkerOptions`.
`PoseLandmarkerResult`	Represents the pose landmarks deection results generated by `PoseLandmarker`.

R

`RetrievalRecord`	Represents a single multi-modal record stored in the vector store.
`RetrievalResult`	Represents a retrieved document or multimedia chunk.
`RunningMode`	MediaPipe audio task running mode.
`RunningMode`	MediaPipe vision task running mode.

S

`ScoreQuestion`	Evaluates an ordered rubric of levels and computes both the most likely rubric level and a continuous expected score in `[0.0, 1.0]`.
`ScoreResult`	Calibrated result of evaluating a `ScoreQuestion`.
`ScoringMode`	Scoring mode for multi-token choice and rubric evaluation.
`SemanticRetriever`	MediaPipe SemanticRetriever API that manages vector embedding and retrieval.
`SemanticRetrieverComponents`	Components used to initialize the SemanticRetriever.
`SqliteVectorStore`	A vector store implementation backed by SQLite database using native SQLite vector engine.
`Stroke`	Represents a single user-drawn stroke for interactive segmentation.
`Stroke.BrushMode`	Specifies the polarity or mode of a brush stroke.
`Stroke.Builder`	Builder for `Stroke`.
`SynthesisOptions`	Per-utterance synthesis overrides passed to `TextToSpeech.synthesize` and `TextToSpeech.synthesizeStream`.

T

`TableConfig`	SQLite table configuration.
`TaskInfo`	`TaskInfo` contains all needed information to initialize a MediaPipe Task `com.google.mediapipe.framework.Graph`.
`TaskInfo.Builder`	Builder for `TaskInfo`.
`TaskOptions`	MediaPipe Tasks options base class.
`TaskResult`	Interface for the MediaPipe Task result.
`TaskRunner`	The runner of MediaPipe task graphs.
`TextChunker`	Interface for chunking long text into smaller segments.
`TextClassifier`	Performs classification on text.
`TextClassifier.TextClassifierOptions`	Options for setting up a `TextClassifier`.
`TextClassifier.TextClassifierOptions.Builder`	Builder for `TextClassifierOptions`.
`TextClassifierResult`	Represents the classification results generated by `TextClassifier`.
`TextEmbedder`	Performs embedding extraction on text.
`TextEmbedder.EmbeddingType`	The embedding task type, used to format input text.
`TextEmbedder.TextEmbedderOptions`	Options for setting up a `TextEmbedder`.
`TextEmbedder.TextEmbedderOptions.Builder`	Builder for `TextEmbedderOptions`.
`TextEmbedder.TextFormatContext`	Encapsulates formatting instructions for models that require it (like Gecko).
`TextEmbedder.TextFormatContext.Builder`	Builder for `TextFormatContext`.
`TextEmbedder.TextRole`	The role of the text in the context of the embedding task.
`TextEmbedderExecutor`	Executor interface to isolate and branch Text Embedder executions.
`TextEmbedderLiteRtLmExecutorImpl`	Helper implementation class for LiteRT-LM Text Embedder integration.
`TextEmbedderResult`	Represents the embedding results generated by `TextEmbedder`.
`TextPart`	Represents a text part of a multi-modal content block.
`TextProofreader`	Performs proofreading on text.
`TextProofreader.ProofreaderResultCallback`	Interface for receiving proofreading results.
`TextProofreader.TextProofreaderOptions`	Holds the configuration for creating a `TextProofreader` instance.
`TextProofreader.TextProofreaderOptions.Builder`	Builder for `TextProofreaderOptions`.
`TextProofreaderResult`	The result of a proofreading operation.
`TextProofreaderResult.Correction`	A single correction.
`TextProofreaderResult.CorrectionType`	The type of correction.
`TextProofreaderStreamingResult`	Represents the streaming proofreading result.
`TextSummarizer`	Performs summarization on text.
`TextSummarizer.SummarizationResultCallback`	Interface for receiving summarization results.
`TextSummarizer.TextSummarizerOptions`	Holds the configuration for creating a `TextSummarizer` instance.
`TextSummarizer.TextSummarizerOptions.Builder`	Builder for `TextSummarizerOptions`.
`TextSummarizer.TextSummarizerOptions.Mode`	The mode of the text summarizer.
`TextSummarizerResult`	Represents the summarization result.
`TextSummarizerStreamingResult`	Represents the streaming summarization result.
`TextToSpeech`	MediaPipe TextToSpeech task interface for Kotlin / Android (Unary + Streaming API).
`TextToSpeechOptions`	Task initialization options for `TextToSpeech` (backed by LiteRT-LM Omni Kokoro-82M).
`TtsStream`	Bidirectional / pull-based streaming synthesis handle supporting Level 2 incremental LLM text pushing (`pushText` + `finishInput`) alongside `readNext` and `cancel`.

U

`UniversalEmbedder`	UniversalEmbedder combines the features of the existing Audio, Text, and Image embedders, while adding support for video embeddings.
`UniversalEmbedderOptions`	Options for setting up a `UniversalEmbedder`.
`UniversalEmbedderOptions.ActivationDataType`	Activation data type for model execution.
`UniversalEmbedderOptions.Builder`	Builder for `UniversalEmbedderOptions`.

V

`VectorStore`	Interface for a vector store.
`VectorStoreRecord`	The memory record entity for vector stores.
`VectorStoreRecord.ContentType`	The content types supported by VectorStoreRecord.
`VoiceInfo`	Voice metadata descriptor returned by `TextToSpeech.listVoices`.

W

WordTimestamp

Word-level timing alignment mapping an input word to audio seconds.