Triggers when a task is run and finished.

Runs a Task

Generate a text response from an audio clip using Gemini models. Useful for summaries, transcripts, and questions about the audio.

Generate a text response from a document using Gemini models. Useful for summaries, key points, and questions about the document.

Generate an image from a text prompt using Gemini or Imagen models.

Bulk runs up to 50,000 tasks using a robot

This is an advanced action which makes a raw HTTP request that includes this integration's authentication.

Sends a chat message, optionally storing messages as you go.

Generate audio from text using Gemini text-to-speech models. Useful for voice responses and audio prompts.

Generate a video from a text prompt using Veo models.