Image and Video

An overview of actions designed for creating, editing, and processing images and video content.

The actions in this category specialize in visual media. They allow your workflows to generate new images from text, edit existing ones, or process video and audio content.

Use these actions to:

• Generate images: Create original images from a text description using models like DALL-E 3.

• Edit images: Perform advanced edits like swapping faces, removing backgrounds, or expanding an image's canvas (outpainting).

• Transcribe audio: Convert audio files into text using models like Whisper.

• Generate speech: Convert text into a spoken audio file.

These tools are perfect for automating content creation, generating product mockups, or making your workflows interactive with audio and video.