Google Gemini

Generate text, chat, and create images using Google Gemini models.

AI and MLAPI key7 actionsAll integrations

On this page

Connect
Call it from a workflow
Actions (7)
chat_gemini
create_video
generate_content
generate_content_from_image
generate_content_with_filesearch
text-to-speech
custom_api_call
Details

Connect

Auth type: API key (secret_text). Paste the API key (or token) from the provider's settings into the connect dialog. It is encrypted at rest and only decrypted on the server when an action runs.

In the editor: Backend panel, Integrations tab, then Connect. This connects it for the project.
For every project in a workspace: Workspace settings, Integrations.
Owners and admins choose which integrations members may connect in the admin panel (Integrations tab), and can attach their own OAuth app there.

Call it from a workflow

Pass the action name and its input. The call resolves with { success, output, error? }; a missing connection resolves with success false and the reason. See ctx.integrations.invoke and ctx.integrations.call.

Native workflow

// .workflow.js (native ctx)
export async function run(ctx) {
  const res = await ctx.integrations.invoke("google_gemini", "chat_gemini", {
    "model": "<model>",
    "prompt": "<prompt>"
  });
  if (!res.success) throw new Error(res.error);
  ctx.log.info("Google Gemini answered", { output: res.output });
}

defineWorkflow module

// defineWorkflow module (@app/sdk ctx)
import { defineWorkflow } from "@app/sdk";

export default defineWorkflow({
  id: "google-gemini-chat-gemini",
  name: "Google Gemini: Chat Gemini",
  description: "Calls Google Gemini when a row is created.",
  trigger: { type: "entity_event", entity: "tickets", event: "created" },
  async run(ctx, event) {
    const res = await ctx.integrations.call("google_gemini", {
      "action": "chat_gemini",
      "model": "<model>",
      "prompt": "<prompt>"
    }) as { success: boolean; error?: string };
    if (!res.success) throw new Error(res.error);
  },
});

From an app (connector proxy)

curl -X POST "$APP_ORIGIN/__appbricx/connector-proxy/google_gemini/chat_gemini" \
  -H "Authorization: Bearer $APP_KEY" \
  -H "content-type: application/json" \
  -d '{"props":{"model":"<model>","prompt":"<prompt>"}}'

Actions

chat_geminiin catalog

Chat Gemini. Chat with Google Gemini

Input	Type	Description
`model`required	id (picked from your account)	The model which will generate the completion
`prompt`required	long text	The prompt to generate content from.
`memoryKey`optional	text	A memory key that will keep the chat history. Keep it empty to leave Gemini without memory of previous messages.

create_videoin catalog

Create Video. Generate a video from a text prompt using Google Veo models.

Input	Type	Description
`model`required	one of "veo-3.1-generate-preview" \| "veo-3.1-fast-generate-preview" \| "veo-3.0-generate-001" \| "veo-3.0-fast-generate-001" \| "veo-2.0-generate-001"	Model
`prompt`required	long text	Describe the video you want to generate. Be specific about the scene, motion, style, and lighting for best results.
`image`optional	file	Optional image to use as the first frame of the video (image-to-video).
`lastFrame`optional	file	Optional image to use as the last frame. Use together with Start Image to generate an interpolation video.
`aspectRatio`required	one of "16:9" \| "9:16"	Aspect Ratio
`durationSeconds`optional	id (picked from your account)	Must be 8 when using 1080p, 4K, or reference images.
`resolution`optional	id (picked from your account)	1080p is available on Veo 3.0+ only. 4K is only available on Veo 3.1 models. 1080p and 4K require 8-second duration.
`personGeneration`optional	one of "allow_adult" \| "allow_all" \| "dont_allow"	Controls whether people or faces can appear in the generated video.

generate_contentin catalog

Generate Content. Generate content using Google Gemini using the "gemini-pro" model

Input	Type	Description
`prompt`required	long text	The prompt to generate content from.
`model`required	id (picked from your account)	The model which will generate the completion
`toolType`optional	one of "google-search" \| "file-search" \| "google-maps" \| "url-context"	Select built-in tool to use with Gemini model.
`toolProperties`optional	object (depends on other props)	Tool Config

generate_content_from_imagein catalog

Generate Content from Image. Generate content using Google Gemini using the "gemini-pro-vision" model

Input	Type	Description
`prompt`required	long text	The prompt to generate content from.
`image`required	file	The image to generate content from.
`model`required	id (picked from your account)	The model which will generate the completion

generate_content_with_filesearchin catalog

Generate Content with File Search. Generate content with file search functionality.

Input	Type	Description
`prompt`required	long text	The prompt to generate content from.
`model`required	id (picked from your account)	The model which will generate the completion
`fileStoreName`required	text	File Store Name
`file`required	file	File

text-to-speechin catalog

Text to Speech. Converts text to audio file.

Input	Type	Description
`model`required	one of "gemini-2.5-pro-preview-tts" \| "gemini-2.5-flash-preview-tts"	Model
`text`required	long text	Input Text
`voice`required	one of "Zephyr" \| "Puck" \| "Charon" \| "Kore" \| "Fenrir" \| "Leda" \| "Orus" \| "Aoede" \| "Callirrhoe" \| "Autonoe" \| "Enceladus" \| "Iapetus"	Voice

custom_api_call

Custom API Call. Make a custom API call to a specific endpoint

Input	Type	Description
`url`required	object (depends on other props)	url
`method`required	one of "GET" \| "POST" \| "PATCH" \| "PUT" \| "DELETE" \| "HEAD"	Method
`headers`required	object	Authorization headers are injected automatically from your connection.
`queryParams`required	object	Query Parameters
`body_type`optional	one of "none" \| "json" \| "form_data" \| "raw"	Body Type
`body`optional	object (depends on other props)	Body
`response_is_binary`optional	boolean	Enable for files like PDFs, images, etc.
`failsafe`optional	boolean	No Error on Failure
`timeout`optional	number	Timeout (in seconds)
`followRedirects`optional	boolean	Follow redirects

Details

Id: google_gemini
Category: AI and ML
Tags: ai, google, gemini, llm, multimodal
Package: @activepieces/piece-google-gemini@0.1.5
Tier: Built in