I am working on a task to record a WebRTC video conversation and then translate it to text.
For recording the audio I am using RecordRTC and for speech recognition I want to use a Web Speech API.
Is it possible to pass a recorded audio track to a Web Speech API and then get text from it? If it is possible - are there are any articles about it?
I was only able to find the articles about Google Speech API but this API is not free...
typescript
, this is written entirely in TypeScript and should work for you: github.com/Azure-Samples/SpeechToText-WebSockets-Javascript – Tyika