Back to top image

Translating with Google AutoML

If you use Google's AutoML MT or Google's Translation LLM, you can integrate either service as a translation provider in Smartling.

Using Smartling's MT Profile feature, you can securely store the Google AutoML credentials in Smartling, and assign the profile to any MT workflow step and even as the MT resource in the CAT Tool. The required credentials are found in an exported JSON file from your Auto ML account. For steps on how to export this JSON file, read the AutoML documentation.

Note: The Google AutoML Translation API will be deprecated and is scheduled to shut down after September 30, 2025. It is recommended that you migrate to Cloud Translation – Advanced to replicate AutoML functionality. See here for more information. Smartling-trained models are not affected by this deprecation.

Permissions

To successfully integrate with Smartling, the following permissions should be granted:

  1. Method: projects.locations.models.list
  2. Method: projects.locations.models.get
  3. Ensure the service user has the following permissions:
    • cloudtranslate.generalModels.predict
    • automl.models.predict
    • cloudtranslate.glossaries.predict

Google Translation LLM

The setup process for using Google's Translation LLM is the same as for Google AutoML.

  • If you already use Google AutoML, you can reuse the same API key, since both services use the Google Cloud Translation v3 API.
  • You will need to create a Google AutoML MT Profile. The setup process is the same as described below, with the difference being that when setting up the MT Profile, you must provide the relevant path to your Google Cloud project in the Model ID field. 
    Example Translation LLM model path: projects/{project-number-or-id}/locations/{location-id}/models/general/translation-llm

Setting up Google AutoML or Google Translation LLM as your translation provider

To use Google AutoML or Google Translation LLM as a provider in Smartling, you first need to create a provider credential and then use it to create an MT Profile.

Creating a provider credential

If you would like to bring your own API key, please create a provider credential in Smartling by following the steps outlined below. Alternatively, reach out to your Smartling Customer Success Manager who can provision provider credentials for you.

  1. From the top navigation of your Smartling dashboard, access the AI Hub.
  2. Navigate to the Credentials section.
    credentials.png
  3. Create a new provider credential
  4. Choose Google AutoML Translation from the MT Provider dropdown. (Select Google AutoML Translation even if you are using Google Translation LLM, since both use the same Google API.)
  5. Select a credential name to reflect the selected provider, as well as any other relevant information
  6. Complete all required fields by entering the credentials from the exported JSON file as follows:
    • Project ID: example_project_id
    • Location: your location will either beus-central1 or eu
    • JSON credentials: copy and paste the entire JSON file into this field, including the brackets

Creating an MT Profile

The provider credential can now be used to create an MT Profile.

  1. From the top navigation of your Smartling dashboard, access the AI Hub.
  2. Click into the Translation Profiles section.
    translation-profiles.png
  3. Click Create MT Profile
  4. Choose Google AutoML Translation from the provider dropdown. (Select Google AutoML Translation even if you are using Google Translation LLM, since both use the same Google API.)
  5. Define a name under Profile Name
    • The name is visible in the Smartling UI
  6. Choose the provider credential you created earlier for Google AutoML.
  7. Complete all required fields:
    • Model ID: This is the custom model name for the entire MT engine, if applicable.
      • /locations/{{your-location}}/models/{{your-model-id}}
      • If you are using Google Translation LLM, be sure to provide the relevant path to the Translation LLM e.g., projects/{project-number-or-id}/locations/{location-id}/models/general/translation-llm
    • Custom Language Code: Use this field only if your custom MT model uses locales which are not supported by Google AutoML, insert the custom language code here.
      • Leave blank to use default language code mapping
    • Glossary ID: Insert custom glossary name, if applicable.
      • Both the Smartling Glossary and your AutoML Glossary work together, meaning the two lists of terms are referenced and used in your translations.
      • Insert the entire path, e.g.: projects/{{your-project-ID}}/locations/{{your-location}}/glossaries/{{your-glossary-ID}}
  8. (Optional) Click Test Integration to ensure that the MT Profile is fully functional.
    • Ensure all fields are complete before testing (including the Profile Name).
  9. (Optional) Define language-specific credentials and rules.
    • This only applies if you have multiple custom models/glossaries and want to use them only for specific language pairs but not others.
    • Bilateral Mode: enabling this feature allows for specific language pairs to be machine translated as both source > target and target > source.
      • This allows you to reverse the language pairs and leverage source content as translations.

Table of Contents