# Eden AI integrations: LLMs, OCR and translation

> Create a chat completion, convert speech to text and generate an image in Eden AI, and start a workflow when Eden AI sends “Async job completed”.

**Canonical page:** https://tray.ai/connectors/eden-ai-integrations/
**Categories:** AI
**Connects through:** HTTP Connector

## Overview

Eden AI is an AI gateway that gives one API to hundreds of models from many providers, covering chat, OCR, translation, speech, and image tasks. Tray.ai connects to Eden AI through the HTTP Connector, so your workflows can call the Eden AI API alongside the rest of your stack.

## Use cases

### LLMs

Read and create llms in Eden AI from any Tray.ai workflow. The Eden AI API covers calls such as create a chat completion and create embeddings.

- Create a chat completion
- Create embeddings
- List LLM models

### OCR

Read and manage ocr in Eden AI from any Tray.ai workflow. The Eden AI API covers calls such as extract text from a document and extract tables.

- Extract text from a document
- Extract tables
- Parse a resume

### Translation

Manage translation in Eden AI from any Tray.ai workflow. The Eden AI API covers calls such as translate text and translate a document.

- Translate text
- Translate a document

### Audio

Create audio in Eden AI from any Tray.ai workflow. The Eden AI API covers calls such as convert speech to text and convert text to speech.

- Convert speech to text
- Convert text to speech

### Images

Create, delete, and manage images in Eden AI from any Tray.ai workflow. The Eden AI API covers calls such as generate an image and remove an image background.

- Generate an image
- Remove an image background
- Detect objects in an image

### Eden AI events

Start a Tray.ai workflow the moment something happens in Eden AI. Eden AI sends events such as async job completed and async job failed to a Tray.ai webhook trigger.

- Async job completed
- Async job failed

## Challenges Tray.ai solves

### Keeping Eden AI credentials out of logs

A raw API call usually means pasting a key or token into the request, where it ends up in step inputs, logs, and screenshots.

**How Tray.ai helps:** Store Eden AI credentials once as a Tray.ai authentication and reference them from the HTTP Connector. Tray.ai masks authentication values in logs, so the secret never shows up in a step's input or output.

### Going from the Eden AI API docs to a working call

Translating an example request from API docs into a workflow step means copying the method, URL, headers, and body by hand.

**How Tray.ai helps:** Paste a cURL example from the Eden AI API docs into the HTTP Connector and Tray.ai fills in the method, URL, headers, and body for you.

### Handling files and non-JSON responses

Not every API answers in JSON. Some return XML, files, or binary data, or expect a multipart upload.

**How Tray.ai helps:** The HTTP Connector parses JSON and XML responses, returns files you can pass to the next step, and sends multipart form data for uploads.

## Frequently asked questions

### Does Tray.ai connect to Eden AI?

Yes. Tray.ai connects to Eden AI through the HTTP Connector, which calls the Eden AI API directly. Any call the Eden AI API documents can run as a step in a Tray.ai workflow.

### How does Tray.ai authenticate with Eden AI?

The Eden AI API uses a bearer token. You save it once as a Tray.ai authentication, and the HTTP Connector adds it to every request.

### Can I get a dedicated Eden AI connector?

Eden AI runs through the HTTP Connector rather than a dedicated connector. If your team wants one, the Tray.ai connector SDK can build a dedicated Eden AI connector from the Eden AI API.

## Learn more

- Intelligent Integration: https://tray.ai/platform/intelligent-ipaas/
- Merlin Agent Builder: https://tray.ai/platform/merlin-agent-builder/
- Agent Gateway for MCP: https://tray.ai/platform/agent-gateway/
- Book a demo: https://tray.ai/contact/