Resources · n8n integration

DeepL n8n integrationAutomate DeepL with n8n.

One node, one job: text goes in, the same text in another language comes out. The DeepL n8n integration exposes a single Translate operation, 2 required fields and 4 optional ones. There is no DeepL trigger node, so the workflow always has to start somewhere else.

Try the DeepL integration on n8nSee the 1 operations

Verified Trustpilot reviews · AI, automation & growth agency

Why automate

What does the DeepL n8n integration actually do?

The DeepL node calls the DeepL API from inside a workflow. It has one resource, Language, and one operation, Translate a language: you give it a text and a target language, it hands back the translation on the same item. The node ships with n8n, on n8n Cloud and on a self-hosted instance, so there is nothing to install and nothing extra to pay on the n8n side.

Depth here comes from the settings, not from the menu. One operation, and four Additional Fields that decide how the output reads. That is the whole surface, and it covers more ground than the short operation list suggests.

Take a support inbox that receives messages in four languages. A Gmail trigger picks up the mail, the DeepL node runs language.translate on the body, and the agent reads one language instead of four. The public template that routes multilingual support requests with DeepL, GPT-3.5 and Gmail is built on exactly that chain.

Second shape: a product catalog that lives in a spreadsheet. Rows come out of Google Sheets, each description runs through the node once per target language, and the translations go back into new columns. Formality set to Formal or Informal keeps every row in the same voice, which matters more on a catalog than on a single message.

Third shape: a channel that mixes languages. A message posted in Slack is translated and reposted, the pattern behind the real-time chat translation template. Here Split Sentences earns its keep, because chat text is full of newlines that are not sentence breaks.

Where the node stops: it translates, and that is it. Anything else the DeepL API offers has no operation in the node, so the HTTP Request node calls that endpoint directly and reuses the same credential through predefined authentication. If you are weighing engines, the Google Translate node is the other built-in option and configures the same way. For the wider picture of the platform, the n8n review goes through what the tool is good at.

Connect

How do you connect DeepL to n8n?

  1. 01

    Open a DeepL developer account

    The credential is built on the DeepL developer program, not on a regular DeepL account. Sign up on the developer side first. n8n works with both the Free and the Pro API plan, so the node itself does not force a choice: pick the plan that matches the volume you expect, and note which one you signed up for, because the next steps depend on it.

  2. 02

    Copy the API Key into n8n

    In n8n, open Credentials, create a DeepL credential and paste the value into the API Key field. A credential is created once and reused by every workflow that needs it, so this is a one-time step. DeepL's authentication documentation shows where the key sits in the developer account if you cannot find it.

  3. 03

    Select the matching API Plan

    The same credential form asks for the API Plan, with two choices: Pro Plan and Free Plan. This is not a label. DeepL exposes a different API endpoint for each plan, and n8n uses your answer to decide which one to call. Set it to the plan your key belongs to, then save the credential and open the node.

Actions

What can the DeepL node do?

The DeepL node exposes 1 operations across 1 resources. For each one: the node as you configure it in n8n, the required fields, and our field notes.

Resources × operations matrix
ResourceTranslate
Language✓

Language

1 operation
01

Translate a language

language.translate

What you see in n8n

Notes & use cases

Sends one text to DeepL and returns the translation on the same item, ready for the next node.

Key parameters

  • Text: the input text, often {{ $json.text }} from the node before.
  • Target Language Name or ID: picked from the list, or set by expression when it changes per item.
  • Source Language Name or ID: optional, for when the incoming language never varies.
  • Split Sentences: Interpunction Only by default; On Punctuation and Newlines suits chat text full of line breaks.
  • Formality: Formal, Informal or Neutral, and not every language supports it.
  • Preserve Formatting: Do Not Correct skips the usual casing and punctuation fixes.
Use cases
turning a support message into the language the team reads.
Need help

Need help automating DeepL with n8n?

A person reads every message.

FAQ

Questions people ask next

01Is the DeepL n8n integration free?
On the n8n side, yes. The DeepL node ships with n8n, so there is nothing to install and no extra cost, and it behaves the same on n8n Cloud and on a self-hosted instance. The DeepL side is separate: the node needs a DeepL developer account, and n8n supports both the Free and the Pro API plan. Which plan you take is a DeepL decision, made on their developer signup, not something n8n changes. The only thing the node cares about is that the API Plan you select in the credential matches the key you pasted next to it.
02What credentials does the DeepL node need?
One credential with two values. DeepL supports a single authentication method for this node, an API key, so there is no OAuth dance and no scope list to review. You paste the key into the API Key field, then tell n8n which API Plan the key belongs to, Pro Plan or Free Plan. The prerequisite is a DeepL developer account, which is a different signup from the regular product. Once saved, the credential shows up in the node's dropdown and can be reused by every other workflow that translates something, without pasting the key again.
03What are the limits of the DeepL node in n8n?
The node does one thing. There is a single resource, Language, and a single operation, Translate a language, so anything else the DeepL API offers has no entry in the node's menu. The fix is the HTTP Request node, which calls any endpoint of the API and reuses the same credential through predefined authentication. Inside the operation you get more room than the menu suggests: Additional Fields carries 4 options, Source Language, Split Sentences, Preserve Formatting and Formality. Preserve Formatting is the one to remember, since Apply Corrections will fix punctuation and casing at sentence boundaries unless you switch it to Do Not Correct.
04Does the DeepL node react in real time?
It does not react at all, because DeepL has no trigger node in n8n. Nothing is listening on the DeepL side, so a workflow that uses it has to be started by something else. Three usual options: a Schedule Trigger that runs on a fixed interval and translates whatever is waiting, an n8n Webhook that a third-party service calls when it has something new, or the trigger of another app in the workflow, which is how the Gmail and Slack patterns work. Put the DeepL node after that trigger and it translates each item as the run goes through.
05n8n or Make for DeepL?
It depends on where you want the workflow to live. Make is hosted by Make, with no self-hosting option, and billed per operation, so a translation workflow that runs on every inbound message has a cost that tracks volume. n8n runs on n8n Cloud or on your own server through Docker or npm, and the workflow is identical either way, which also means the text you translate can stay inside infrastructure you control. Both give you a visual canvas. Pick Make if you want nothing to maintain, pick n8n if hosting, data control and the cost model matter more than that.
Same platform

Other docs you might need on this stack.

Browse all integrations