> ## Documentation Index
> Fetch the complete documentation index at: https://docs.definable.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Multimodal Input

> Send images, audio, video, and files to models and agents.

Definable provides unified media types that work across all providers supporting multimodal input.

## Images

```python theme={null}
from definable.agent import Agent
from definable.media import Image

agent = Agent(model="gpt-4o", instructions="Describe images in detail.")

output = await agent.arun(
    "What do you see?",
    images=[Image(url="https://example.com/photo.jpg")],
)
print(output.content)
```

### Image Sources

<CodeGroup>
  ```python URL theme={null}
  image = Image(url="https://example.com/photo.jpg")
  ```

  ```python Local file theme={null}
  image = Image(filepath="/path/to/photo.png")
  ```

  ```python Base64 theme={null}
  image = Image.from_base64(base64_string, format="png")
  ```

  ```python Raw bytes theme={null}
  image = Image(content=raw_bytes, format="jpeg")
  ```
</CodeGroup>

## Audio

```python theme={null}
from definable.media import Audio

output = await agent.arun(
    "Transcribe this audio.",
    audio=[Audio(filepath="/path/to/audio.mp3")],
)
```

<Note>
  Most models do not support raw audio input. Use `audio_transcriber=True` on the agent to automatically transcribe audio to text before the model sees it.
</Note>

## Files

```python theme={null}
from definable.media import File

output = await agent.arun(
    "Summarize this document.",
    files=[File(filepath="/path/to/report.pdf")],
)
```

When [readers](/readers/overview) are enabled on the agent, file content is automatically extracted and injected into the prompt.

## Video

```python theme={null}
from definable.media import Video

output = await agent.arun(
    "Describe what happens in this video.",
    videos=[Video(url="https://example.com/video.mp4")],
)
```

## Voice Note Transcription

For Telegram/Discord voice messages, enable the audio transcriber:

```python theme={null}
agent = Agent(model="gpt-4o", audio_transcriber=True)  # Uses OpenAI Whisper
```

See [Agent configuration](/agents/configuration#audio-transcription) for details.