The Microsoft Video Indexer service extracts valuable insights from videos, such as spoken words, faces, characters and emotions. The service supports many of the major world languages (but not every language, e.g. Dutch). Zoom Media offers speech to text in other Languages, including Dutch. Viktor Pikula created a description of how you can use our speech to text service in conjunction with Microsoft Video Indexer.
The PowerShell script included in this repo will deploy a set of Azure resources that integrate the Microsoft Video Indexer service with Zoom Media’s speech-to-text service. This script can be easily updated to work with other transcription service providers to cover a broader range of languages.