> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Multimodal Agents

> Build agents that process and generate images, audio, video, and files.

Agno agents support multimodal input and output using text, image, audio, video and files.

## Guides

**Images**

> **[Image As Input](https://agno-v2.mintlify.site/multimodal/agent/usage/image-input.md)**
>
> Analyze and describe images with agents.

> **[Image As Output](https://agno-v2.mintlify.site/multimodal/agent/usage/image-output.md)**
>
> Return generated images from agent responses.

> **[Image to Text](https://agno-v2.mintlify.site/multimodal/agent/usage/image-to-text.md)**
>
> Convert input image to text.

> **[OpenAI Image Generation](https://agno-v2.mintlify.site/multimodal/agent/usage/image-generation.md)**
>
> Generate images with OpenAI tool.

> **[Image Generation](https://agno-v2.mintlify.site/multimodal/agent/usage/generate-image.md)**
>
> Legacy DalleTools example for image generation.

> **[Image Analysis in Same Run](https://agno-v2.mintlify.site/multimodal/agent/usage/agent-same-run-image-analysis.md)**
>
> Legacy DalleTools example for generation and same-run analysis.

> **[Image Analysis in Multi-turn Runs](https://agno-v2.mintlify.site/multimodal/agent/usage/agent-using-multimodal-tool-response-in-runs.md)**
>
> Legacy DalleTools example for generation and multi-turn analysis.

> **[Image I/O with Fal API](https://agno-v2.mintlify.site/multimodal/agent/usage/image-to-image-agent.md)**
>
> Use input image and Fal API to generate new images.

> **[Image to Structured Output](https://agno-v2.mintlify.site/multimodal/agent/usage/image-to-structured-output.md)**
>
> Convert input image to structured output using Pydantic models.

> **[Generate Image with Intermediate Steps](https://agno-v2.mintlify.site/multimodal/agent/usage/generate-image-with-intermediate-steps.md)**
>
> Legacy DalleTools example with intermediate run events.

> **[High Fidelity Image Analysis](https://agno-v2.mintlify.site/multimodal/agent/usage/image-input-high-fidelity.md)**
>
> Analyze images with high fidelity.

> **[Image to Audio](https://agno-v2.mintlify.site/multimodal/agent/usage/image-to-audio.md)**
>
> Convert input image to audio.

> **[Image input for Tools](https://agno-v2.mintlify.site/multimodal/agent/usage/image-input-for-tool.md)**
>
> Legacy example that passes uploaded and DALL-E-generated images to tools.

**Audio**

> **[Audio As Input](https://agno-v2.mintlify.site/multimodal/agent/usage/audio_input.md)**
>
> Analyze and understand audio input with agents.

> **[Audio As Output](https://agno-v2.mintlify.site/multimodal/agent/usage/audio_output.md)**
>
> Return audio responses from agents.

> **[Audio I/O](https://agno-v2.mintlify.site/multimodal/agent/usage/audio-input-output.md)**
>
> Use audio as input and output in agents.

> **[Generate Music](https://agno-v2.mintlify.site/multimodal/agent/usage/generate-music-agent.md)**
>
> Generate classical music using agents.

> **[Speech-to-Text](https://agno-v2.mintlify.site/multimodal/agent/usage/audio-to-text.md)**
>
> Transcribe audio conversations with Gemini.

> **[Audio Generation](https://agno-v2.mintlify.site/multimodal/agent/usage/audio_generation.md)**
>
> Generate speech and sound effects with ElevenLabs.

> **[Multi-turn Audio](https://agno-v2.mintlify.site/multimodal/agent/usage/audio-multi-turn.md)**
>
> Multi-turn audio conversation with AI models.

> **[Audio Streaming](https://agno-v2.mintlify.site/multimodal/agent/usage/audio-streaming.md)**
>
> Stream audio responses from agents.

> **[Audio Sentiment Analysis](https://agno-v2.mintlify.site/multimodal/agent/usage/audio-sentiment-analysis.md)**
>
> Analyze sentiment of audio using agents.

> **[Convert Blog to Podcast](https://agno-v2.mintlify.site/multimodal/agent/usage/blog-to-podcast.md)**
>
> Convert blog to podcast using agents.

**Video**

> **[Video Input](https://agno-v2.mintlify.site/multimodal/agent/usage/video_input.md)**
>
> Analyze and understand video input with agents.

> **[Video Output](https://agno-v2.mintlify.site/multimodal/agent/usage/video_generation.md)**
>
> Generate video output using FAL.

> **[Generate Video Captions](https://agno-v2.mintlify.site/multimodal/agent/usage/video-caption.md)**
>
> Use video as input to generate captions.

> **[Generate Shorts](https://agno-v2.mintlify.site/multimodal/agent/usage/video-to-shorts.md)**
>
> Generate Shorts from Video.

> **[Generate Video with Replicate](https://agno-v2.mintlify.site/multimodal/agent/usage/generate-video-using-replicate.md)**
>
> Generate video using Replicate.

> **[Generate Video with ModelsLab](https://agno-v2.mintlify.site/multimodal/agent/usage/generate-video-using-models-lab.md)**
>
> Generate video using ModelsLab.

**Files**

> **[File Input](https://agno-v2.mintlify.site/multimodal/agent/usage/file_input.md)**
>
> Process files like PDFs as input to agents.

> **[File Output](https://agno-v2.mintlify.site/multimodal/agent/usage/file_generation.md)**
>
> Use Agno FileGenerationTools to generate files.

> **[File Input for Tools](https://agno-v2.mintlify.site/multimodal/agent/usage/file-input-for-tool.md)**
>
> Use Agno FileInputTools to receive files as input.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.