> ## Documentation Index > Fetch the complete documentation index at: https://docs.gbox.ai/llms.txt > Use this file to discover all available pages before exploring further. # Type text > Directly inputs text content without triggering physical key events (keydown, etc.), ideal for quickly filling large amounts of text when intermediate input events aren't needed. ## OpenAPI ````yaml post /boxes/{boxId}/actions/type openapi: 3.0.0 info: title: GBOX Open API description: GBOX Open API Documentation version: '1.0' contact: {} servers: - url: https://gbox.ai/api/v1 description: Production Server security: [] tags: [] paths: /boxes/{boxId}/actions/type: post: tags: - UI Action summary: Type text description: >- Directly inputs text content without triggering physical key events (keydown, etc.), ideal for quickly filling large amounts of text when intermediate input events aren't needed. operationId: UIActionController_type parameters: - name: boxId required: true in: path description: Box ID schema: example: c9bdc193-b54b-4ddb-a035-5ac0c598d32d type: string requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/Type' examples: Basic: summary: Type text value: text: Hello World responses: '200': description: '' content: application/json: schema: $ref: '#/components/schemas/ActionResult' security: - bearer: [] x-codeSamples: - lang: JavaScript source: |- import GboxSDK from "gbox-sdk"; const gboxSDK = new GboxSDK({ apiKey: process.env["GBOX_API_KEY"] // This is the default and can be omitted }); async function main() { const box = await gboxSDK.create({ type: "android" }); await box.action.type({ text: "Hello, World!" }); // Type and press Enter await box.action.type({ text: "search gbox", pressEnter: true }); } main(); - lang: Python source: |- import os from gbox_sdk import GboxSDK def main(): gbox_sdk = GboxSDK(api_key=os.environ["GBOX_API_KEY"]) # This is the default and can be omitted # Create Android box box = gbox_sdk.create(type="android") # Type text box.action.type(text="Hello, World!") # Type and press Enter box.action.type(text="search gbox", press_enter=True) if __name__ == "__main__": main() - lang: Go source: "package main\n\nimport (\n\t\"context\"\n\t\"fmt\"\n\t\"log\"\n\t\"os\"\n\n\t\"github.com/gbox/gbox-sdk-go\"\n)\n\nfunc main() {\n\tgboxSDK := gbox.NewGboxSDK(os.Getenv(\"GBOX_API_KEY\"))\n\n\tbox, err := gboxSDK.Create(context.Background(), gbox.CreateBoxRequest{\n\t\tType: \"android\",\n\t})\n\tif err != nil {\n\t\tlog.Fatalf(\"Failed to create box: %v\", err)\n\t}\n\n\n err = box.Action.Type(context.Background(), gbox.TypeRequest{\n Text: \"Hello, World!\",\n })\n\tif err != nil {\n\t\tlog.Fatalf(\"Failed to perform type action: %v\", err)\n\t}\n\n // Type and press Enter\n err = box.Action.Type(context.Background(), gbox.TypeRequest{\n Text: \"search gbox\",\n PressEnter: true,\n })\n if err != nil {\n log.Fatalf(\"Failed to perform type action with Enter: %v\", err)\n }\n}" components: schemas: Type: type: object properties: text: type: string description: Text to type example: Hello, World! mode: type: string enum: - append - replace description: >- Text input mode: 'append' to add text to existing content, 'replace' to replace all existing text default: append example: append pressEnter: type: boolean description: Whether to press Enter after typing the text default: false example: false options: description: >- Action options. When `options.screenshot` is provided, ALL deprecated screenshot fields (outputFormat, presignedExpiresIn, screenshotDelay, screenshotRange, includeScreenshot) will be completely ignored. example: screenshot: outputFormat: base64 presignedExpiresIn: 30m delay: 500ms phases: - before - after allOf: - $ref: '#/components/schemas/ActionCommonOptions' title: Type Action description: Text typing action configuration required: - text ActionResult: type: object properties: message: type: string description: message example: Action executed successfully actionId: type: string description: >- Unique identifier for each action. Use this ID to locate the action and report issues. example: c9bdc193-b54b-4ddb-a035-5ac0c598d32d screenshot: description: >- Optional screenshot data. Only present when screenshots are requested via options.screenshot.phases or deprecated fields example: trace: uri: data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAUA... before: uri: data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAUA... after: uri: data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAUA... allOf: - $ref: '#/components/schemas/ActionResultScreenshot' title: Action Result description: Result of an UI action execution with optional screenshots required: - message - actionId ActionCommonOptions: type: object properties: screenshot: description: >- Screenshot options. Can be a boolean to enable/disable screenshots, or an object to configure screenshot options. oneOf: - $ref: '#/components/schemas/ActionScreenshotOptions' example: outputFormat: base64 presignedExpiresIn: 30m delay: 500ms phases: - before - after - type: boolean example: true model: type: string description: >- Model to use for natural-language target resolution. Defaults to 'uitars'. enum: - gpt-5 - gpt-4o - gelato - ui-tars - openai-computer-use default: gelato title: Action Common Options description: Action common options ActionResultScreenshot: type: object properties: trace: description: URI of the screenshot before the action with operation trace example: uri: data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAUA... allOf: - $ref: '#/components/schemas/ActionResultOperationTrace' before: description: URI of the screenshot before the action example: uri: data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAUA... allOf: - $ref: '#/components/schemas/ActionResultScreenshotBefore' after: description: URI of the screenshot after the action example: uri: data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAUA... allOf: - $ref: '#/components/schemas/ActionResultScreenshotAfter' title: Action Result Screenshot description: Complete screenshot result with operation trace, before and after images ActionScreenshotOptions: type: object properties: outputFormat: type: string enum: - base64 - storageKey description: Type of the URI. default is base64. default: base64 example: base64 presignedExpiresIn: type: string description: >- Presigned url expires in. Only takes effect when outputFormat is storageKey. Supported time units: ms (milliseconds), s (seconds), m (minutes), h (hours) Example formats: "500ms", "30s", "5m", "1h" Default: 30m example: 30m default: 30m title: PresignedExpiresIn delay: type: string description: >- Delay after performing the action, before taking the final screenshot. Execution flow: 1. Take screenshot before action 2. Perform the action 3. Wait for screenshotDelay (this parameter) 4. Take screenshot after action Example: '500ms' means wait 500ms after the action before capturing the final screenshot. Supported time units: ms (milliseconds), s (seconds), m (minutes), h (hours) Example formats: "500ms", "30s", "5m", "1h" Default: 500ms Maximum allowed: 30s example: 500ms default: 500ms title: Delay phases: type: array description: >- Specify which screenshot phases to capture. Available options: - before: Screenshot before the action - after: Screenshot after the action - trace: Screenshot with operation trace Default captures all three phases. Can specify one or multiple in an array. If empty array is provided, no screenshots will be taken. default: - before - after - trace example: - before - after items: type: string enum: - before - after - trace title: Action Screenshot Options description: Action screenshot options ActionResultOperationTrace: type: object properties: uri: type: string description: URI of the screenshot with operation trace example: data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAUA... title: Action Result Screenshot Operation Trace description: Screenshot with action operation trace required: - uri ActionResultScreenshotBefore: type: object properties: uri: type: string description: URI of the screenshot before the action example: data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAUA... presignedUrl: type: string description: Presigned url of the screenshot before the action example: https://example.com/xxxxx/xxxxx/xxxxx title: Action Result Screenshot Before description: Screenshot taken before action execution required: - uri ActionResultScreenshotAfter: type: object properties: uri: type: string description: URI of the screenshot after the action example: data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAUA... presignedUrl: type: string description: Presigned url of the screenshot before the action example: https://example.com/xxxxx/xxxxx/xxxxx title: Action Result Screenshot After description: Screenshot taken after action execution required: - uri securitySchemes: bearer: scheme: bearer bearerFormat: JWT type: http description: >- Enter your API Key in the format: Bearer . Get it from https://gbox.ai ````