Workshops Use Cases Architecture Projects Blog
About Contact Offers Talks
Home›AI technologies›Machine translationDeutsch

Machine translation: text from one language into another

Neural machine translation moves text between languages at a fixed price per character, and respects a glossary of terms you insist on.

Amazon TranslateAzure AI TranslatorCloud TranslationNLLB or Opus-MT
Book a free 30-min call →AI Concept and Prototype workshops →

What is machine translation?

A translation service takes text plus a source and target language and returns the translation. Custom terminology, a glossary of your product names and fixed terms, is the part worth maintaining: it is why your names survive the translation.

It feels like a model problem, and it is a product you call. For legal or medical documents, machine translation is a draft, never the final text.

Goes inText, plus the source and target language
Comes outThe translation, respecting your glossary
Typical usesSupport tickets, product texts, subtitles, internal documents

Four ways to run it

Each of the big clouds offers it as a managed service, and you can also run it yourself. Same task, a different bill and a different console.

Amazon Translate
Managed on AWS

Amazon Translate[1]

The managed neural translation service on AWS, priced per character, with custom terminology at no extra cost.

Official documentation →
Azure AI Translator
Managed on Microsoft Azure

Azure AI Translator[2]

The managed translation service on Microsoft Azure, for text and documents.

Official documentation →
Cloud Translation
Managed on Google Cloud

Cloud Translation[3]

The managed translation API on Google Cloud.

Official documentation →
NLLB or Opus-MT
Run it yourself

NLLB or Opus-MT[4]

Open translation models you run yourself. Check the licence per model: Meta's NLLB-200 is licensed CC BY-NC 4.0, non-commercial; Opus-MT models from the University of Helsinki are published per language pair, for example Apache 2.0.

Project page →
Amazon Translate: The managed service on one page, with the same service on the other platforms.
The managed service on one page, with the same service on the other platforms.[5]

How it looks in an architecture

Slides from my course on AI architectures at FH Burgenland, drawn from real projects.

Ready-made AI services share one shape: a trained model you never see, reached by an API.
Ready-made AI services share one shape: a trained model you never see, reached by an API.[6]
The same job on AWS, Azure, Google Cloud and on your own ground.
The same job on AWS, Azure, Google Cloud and on your own ground.[5]

Where I used it

Translation is not part of my three reference projects. One thing I do see often: teams fine-tuning a model for translation, where a managed service with a glossary would do.

Managed and self-hosted together: hybrid

With a ready-made service the call leaves your network. The hybrid decision is what crosses, and in what state: the whole file, a redacted one, or only the part that has to. Where a file may not leave at all, the same step runs with the open-source option inside your building, and only the result, or nothing, crosses.[7]

Hybrid is a decision at every layer. For translation the question is which text may be sent out.
Hybrid is a decision at every layer. For translation the question is which text may be sent out.[8]

What would help you next?

Learn to decide

The course “From Managed to Hybrid” teaches where AI should run: what each layer costs, what you operate and where your data has to stay. It is in preparation, with a free live session first.

Join the course waitlist →
Linda MohamedLinda Mohamed
AI and cloud consultant, AWS Community Hero, Vienna

Build it with me

Tell me what you want to build. In 30 minutes we check which of the four ways fits your data, your rules and your budget, and whether AWS funding for a proof of concept can cover part of it. How AWS funding works →

Book a free 30-min call →15-min question slot

You already know what you need

Book the workshop directly:

ai-solutions.wiki

Read more on ai-solutions.wiki

My open knowledge base, with longer comparisons, pricing notes and sources.

Sources

  1. Amazon Translate documentation. https://docs.aws.amazon.com/translate/latest/dg/what-is.html
  2. Azure AI Translator documentation. https://learn.microsoft.com/en-us/azure/ai-services/translator/overview
  3. Cloud Translation documentation. https://cloud.google.com/translate/docs
  4. NLLB or Opus-MT. https://huggingface.co/Helsinki-NLP/opus-mt-de-en
  5. Linda Mohamed, course slides “The projects”, MASE-3, FH Burgenland, September 2026
  6. Linda Mohamed, course slides “How to run AI, layer by layer”, MASE-3, FH Burgenland, September 2026
  7. NIST glossary: hybrid cloud. https://csrc.nist.gov/glossary/term/hybrid_cloud
  8. Linda Mohamed, course slides “Start here”, MASE-3, FH Burgenland, September 2026
  9. Amazon Translate, ai-solutions.wiki. https://ai-solutions.wiki/tools/amazon-translate/
  10. Azure Translator, ai-solutions.wiki. https://ai-solutions.wiki/tools/azure-translator/
  11. Hugging Face, ai-solutions.wiki. https://ai-solutions.wiki/tools/huggingface/
  12. NLLB-200 model card, licence CC BY-NC 4.0. https://huggingface.co/facebook/nllb-200-distilled-600M

Links checked September 2026. Product names and features change: check the linked pages before you decide.