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

# OpenAI

> Images, image edits and speech from OpenAI. The default way Boost makes a picture or a voice-over for a page.

Images, image edits and speech from OpenAI. The default way Boost makes a picture or a voice-over for a page.

## Connecting

In the dashboard, open **Connectors**, find OpenAI and press **Connect**. The key you enter is checked against OpenAI before anything is saved, so a key that is refused never becomes a connection that fails later.

### What you will need

| Field   | What it is          |
| ------- | ------------------- |
| API Key | Your OpenAI API key |

### Getting the credential

1. Go to [OpenAI Platform](https://platform.openai.com/api-keys) and create an API key
2. Paste it into the connector

## Notes

* Results are copied onto BoostGPT storage, so the link keeps working.
* `mask.image_url` is optional: supply a PNG whose transparent areas mark the region to change, or leave it out
  and let the prompt describe the edit.

## What an agent can do with it

| Tool              | What it does                                                                                                                                                                                   |
| ----------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `generate_image`  | Generate an image from a text prompt with GPT-Image. Returns a hosted URL.                                                                                                                     |
| `edit_image`      | Edit an existing image from a text instruction — for example removing a background or changing a colour. Pass the image by URL; an attached photo's link works directly. Returns a hosted URL. |
| `generate_speech` | Convert text to speech using OpenAI TTS models. Returns raw audio binary in the requested format.                                                                                              |

## Useful resources

* [OpenAI images guide](https://platform.openai.com/docs/guides/images)