Runway

Generate videos and images using Runway's AI creative tools.

AI and MLAPI key4 actionsAll integrations

On this page

Connect
Call it from a workflow
Actions (4)
cancel_or_delete_task
generate_image_from_text
generate_video_from_image
get_task_details
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("runway", "cancel_or_delete_task", {
    "taskId": "<task id>"
  });
  if (!res.success) throw new Error(res.error);
  ctx.log.info("Runway answered", { output: res.output });
}

defineWorkflow module

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

export default defineWorkflow({
  id: "runway-cancel-or-delete-task",
  name: "Runway: Cancel or Delete Task",
  description: "Calls Runway when a row is created.",
  trigger: { type: "entity_event", entity: "tickets", event: "created" },
  async run(ctx, event) {
    const res = await ctx.integrations.call("runway", {
      "action": "cancel_or_delete_task",
      "taskId": "<task id>"
    }) 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/runway/cancel_or_delete_task" \
  -H "Authorization: Bearer $APP_KEY" \
  -H "content-type: application/json" \
  -d '{"props":{"taskId":"<task id>"}}'

Actions

cancel_or_delete_taskin catalog

Cancel or Delete Task. Cancel or delete a task. Running/pending tasks are cancelled, completed tasks are deleted.

Input	Type	Description
`taskId`required	text	The ID of the task to cancel or delete (UUID format)

generate_image_from_textin catalog

Generate Image From Text. Generates an image using a text prompt via Runway's AI models

Input	Type	Description
`model`required	one of "gen4_image" \| "gen4_image_turbo"	AI model to use for image generation
`promptText`required	long text	Describe what you want to see in the image (max 1000 characters)
`ratio`required	one of "1920:1080" \| "1080:1920" \| "1024:1024" \| "1360:768" \| "1080:1080" \| "1168:880" \| "1440:1080" \| "1080:1440" \| "1808:768" \| "2112:912" \| "1280:720" \| "720:1280"	Resolution of the output image
`seed`optional	number	Random seed for reproducible results (0-4294967295)
`referenceImages`optional	array	Up to 3 reference images (required for gen4_image_turbo)
`publicFigureThreshold`optional	one of "auto" \| "low"	How strict content moderation should be for recognizable public figures

generate_video_from_imagein catalog

Generate Video From Image. Generates a video based on image(s) and text prompt using Runway's AI models

Input	Type	Description
`model`required	one of "gen4_turbo" \| "gen3a_turbo" \| "veo3"	AI model to use for video generation
`promptImageFile`optional	file	Upload an image file to use as the video's starting frame
`promptImageUrl`optional	text	HTTPS URL of an image to use as the video's starting frame
`imagePosition`optional	one of "first" \| "last"	Position of the image in the video (last frame only supported by gen3a_turbo)
`promptText`optional	long text	Describe what should happen in the video (max 1000 characters)
`ratio`required	object (depends on other props)	Available resolutions depend on the selected model
`duration`required	object (depends on other props)	Available durations depend on the selected model
`seed`optional	number	Random seed for reproducible results (0-4294967295)
`contentModeration`optional	object (depends on other props)	Content moderation settings (not available for veo3)

get_task_detailsin catalog

Get Task Details. Retrieve details of an existing Runway task by its ID

Input	Type	Description
`taskId`required	text	The unique ID of the task to retrieve (UUID format)
`downloadOutput`optional	boolean	Download and return the generated files as attachments (if task succeeded)

Details

Id: runway
Category: AI and ML
Tags: video, image, generation, creative, ai
Package: @activepieces/piece-runway@0.1.3
Tier: Community