Speech-To-Text is one of the components of our Multimodal Indexing AI, that allows for an automatic transcription of all spoken words detected in a video.
We supported 27 languages until now, and we just released a new list of 140 languages. Here are some of the most anticipated:
Automatic transcription of your live streams and archives not only helps tremendously with your editorial tasks but is also used to index your media assets. This means you can search for any verbal quote detected in your pool of media assets.
If the videos are also automatically translated, this means you can search in any of the languages (the source language or the translated version) and get retrieval matches.
Just imagine the possibilities! ✨
👉🏽 If you wish to activate a new language in your workspace, please contact your admin and/or Moments Lab customer support manager.
Find below the full list of languages supported by Moments Lab: