📅
⏱️ 1 min read (176 words)
I recently embarked on a small side project where Azure Cognitive Services, specifically the speech aspect will be used. I started to read the documentation which seems relatively straight forward. I went on to deploy an instance into my Azure sandbox.
I am specifically interested right now in the speech to text and the text to speech aspect. I also saw hidden in the documentation examples of pronounciation assessments, which I suspect I will use at some point later.
Here’s an example written in python which I setup to test out cognitive services. I was able to get some basic speech to text functionality working.
The next step is to look at getting the speech from a browser window using javascript and pass that into the API backend. I did have a go at doing this but seem to be struggling with getting the correct audio format and stream from the front end to the backend. I set this up using Flask.
Health ❤️ ❤️ ❤️ ❤️ 💔
Come back soon for the next quest 🏹