# Annotations

Add annotations to your data to make analysis and collaboration easier. Annotations added to a dataset are visible across all projects and can be viewed by every user in your workspace. To get started, hover over a plot, place your cursor at the desired timestamp, and create a new annotation. The screenshot below shows the process.

<figure><img src="/files/Bmd0YK7HVJ2vYSSXotVj" alt="Annotations on a time series plot"><figcaption></figcaption></figure>

## Automatic generation of annotations

Annotations can be generated directly from recorded audio files (`.wav`, `.mp3`, `.m4a`, ...) by using a speech decoding tool (e.g. [Whisper](https://github.com/openai/whisper)) in combination with [Marple's SDK](/docs/sdk/overview.md).

Read more:

* Our blog post ["Automatic Extraction of Radio Comms Using Agentic Coding"](https://www.marpledata.com/resources/automatic-extraction-of-radio-comms-to-marple-using-agentic-coding)
* [Agentic Coding](/docs/sdk/agentic-coding.md)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.marpledata.com/docs/marple-insight/user-manuals/visualisation/annotations.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
