Skip to main content
Agno provides comprehensive multimodal support, enabling agents and teams to process and generate content across multiple formats including text, images, audio, video, and files. This allows you to build sophisticated AI applications that can understand and create rich media content. Multimodal capabilities enable powerful use cases such as image analysis with contextual responses, audio transcription and generation, video processing, and document understanding. For a complete overview of model compatibility and supported modalities, please check out the compatibility matrix.
To get started, take a look at the multimodal examples.

​
Learn more

Agent

Learn how to create multimodal agents in Agno.

Team

Learn how to create multimodal teams in Agno.

​
Images

Image As Input

Learn how to use image as input with Agno agents.

Image As Output

Learn how to use image as output with Agno agents.

Image Generation

Learn how to use image generation with Agno agents.

​
Audio

Audio As Input

Learn how to use audio as input with Agno agents.

Audio As Output

Learn how to use audio as output with Agno agents.

Speech-to-Text

Learn how to use speech-to-text with Agno agents.

Audio Generation

Learn how to use audio generation with Agno agents.

​
Video

Video As Input

Learn how to use video as input with Agno agents.

Video Generation

Learn how to use video generation with Agno agents.

​
Files

Files As Input

Learn how to use files as input with Agno agents.

Files Generation

Learn how to use files generation with Agno agents.