Ever wish you could instantly transcribe an interview, a video or a podcast? We are about to launch speech-to-text-models in all of the Nordic languages - and we're starting with Danish.
Furthering our mission to build AI features that understand media as humans do, we are making remarkable progress within speech-to-text technology.
Since the first version was launched, speech-to-text technology has faced considerable challenges related to accuracy. But we have been constantly improving performance relating to background noise, punctuation placement, capitalization, correct formatting, timing of words, speaker identification, terminology, etc. So much so that we now have the worlds best speech-to-text model in Danish - ready to speed up everything from your journalistic content efforts to functionalities within your apps, services etc.
Within the 2022 general elections context in Denmark, we applied and tested it at the party leader's debate (see below).
Notice the "speaker ID" at the top of the video (and the subtitles generated by our speech-to-text model, not least!). Speaker ID makes it easy to identify who is saying what in transcripts, when you get a transscription of a video or audio file.
The MediaCatch speech-to-text technology can be applied to any piece of audio-carrying content, making it visually understandable and easy to digest at speed. It's being trained concurrently to understand multiple tones, sentiments and contexts across audio carrying content.
If you are interested in learning more about our speech-to-text feature, or how AI can help you supercharge your companys processes and workflows, you can subscribe to our newsletter, or drop us a message via the contact form.
Or contact Carsten Lakner to get more information
Book a meeting with our Chief Data Scientist, Cæcilie, or one of our other great colleagues. We’ll make sure to find the right AI solution that will super power the needs of your business.