Today, the Document Translation feature of Translator is in general availability. Document Translation was launched in public preview back in February of this year and is now generally available. This new Translator service translates entire documents, or batches of documents, in a variety of file formats preserving their original structure and format.
Document Translation was specifically designed to translate large files with rich content — translate Word, PowerPoint, Excel, or PDFs, and more into 90 languages and dialects. You can also apply custom glossaries and custom models built with Custom Translator to make sure your documents translate the way you want.
Based on your feedback during the Document Translation preview, we have made updates to improve your translation experience:
- Translate a variety of file formats: Document Translation supports current and legacy Office formats for Word, PowerPoint, Excel, and Outlook (.doc, .docx, .ppt, .pptx, .xls, .xlsx, and .msg); Plain and Rich Text (.txt and .rtf); HTML files (.html and .htm); Tab and Comma Separated Values (.tsv, .tab, .csv), XML Localization Interchange Files (.xlf); and Open Document Text, Presentations, and Spreadsheets (.odt, .odp, and .ods).
- Automatically detect language of documents: You don’t need to explicitly tell the service which language your documents are in, just submit them for translation and the service will automatically detect it.
- Translate documents that have content in multiple languages: If your documents include more than one language, the document translation will translate them all into the target language. For instance, if you have a document that has some portions in French, some in German, and some in Spanish, you could translate the entire document into English with no additional steps, and without having to break up the document into separate pieces for each language.*
- Translate documents into multiple languages: You can translate documents into multiple languages in a single request.
- Translate single files or multiple files at the same time: You can translate all the files in an Azure blob storage container, all documents within a specific folder in a container, or even just a single document within a container.
- Job status filtering: The Get Translations and Get Documents methods now have multiple ways to filter the status of large jobs.
- Security and authentication options: You can use Managed Identity or a Shared Access Signature to establish access between the service and storage and authenticate your translation request with Azure Active Directory or Azure API Management.
Two pricing plans are available for Document Translation through Azure — the Pay-as-you-go plan or the D3 volume discount plan which allows you to save money compared for higher volumes of Document Translation. Learn more on at aka.ms/TranslatorPricing.
Learn more about Document Translation and how to get started in Translator’s online documentation at aks.ms/TranslatorDocs.
References:
*This feature is intended for complete sentences in a single language. If sentences are composed of more than one language, the translation could be suboptimal.
