<br />

Multimodal decision input combining text, encoded image bytes, and/or 16kHz mono PCM audio samples.

**Signature:**

    export declare interface DecisionContextInput 

## Properties

| Property | Modifiers | Type | Description |
|---|---|---|---|
| [text](https://developers.google.com/edge/api/mediapipe/js/tasks-decision.decisioncontextinput#decisioncontextinputtext) |   | string | Optional text context or query description. |
| [imageBytes](https://developers.google.com/edge/api/mediapipe/js/tasks-decision.decisioncontextinput#decisioncontextinputimagebytes) |   | Uint8Array | Optional raw encoded image bytes (PNG, JPEG, WebP, or TGA). |
| [audioSamples](https://developers.google.com/edge/api/mediapipe/js/tasks-decision.decisioncontextinput#decisioncontextinputaudiosamples) |   | Float32Array | Optional mono 16kHz PCM audio samples in \[-1.0, 1.0\]. |

## DecisionContextInput.text {#decisioncontextinputtext}

Optional text context or query description.

**Signature:**

    text?: string;

## DecisionContextInput.imageBytes {#decisioncontextinputimagebytes}

Optional raw encoded image bytes (PNG, JPEG, WebP, or TGA).

**Signature:**

    imageBytes?: Uint8Array;

## DecisionContextInput.audioSamples {#decisioncontextinputaudiosamples}

Optional mono 16kHz PCM audio samples in \[-1.0, 1.0\].

**Signature:**

    audioSamples?: Float32Array;