IBM Watson Speech To Text

Simple applcation on how to use IBM Watson Speech To Text service, which converts the given audio file to text

This code example use the client library that is provided for .NET Standard.

dotnet add package IBM.Watson.SpeechToText.v1 --version 5.1.0

You authenticate to the API by using IBM Cloud Identity and Access Management (IAM).

You can pass either a bearer token in an authorization header or an API key, for this example I used API key.

First you need to subscribe to Speech to Text service from IBM's cloud shell from there you will get {apikey} and {apiServiceUrl} You pass in the {apikey} and {apiServiceUrl} in config file Transcriber.dll.Config section.

	<appSettings>
		<add key="apiKey" value="XXXXXXXXXXXXXXXXXXXXXXXX"/>
		<add key="apiServiceUrl" value="XXXXXXXXXXXXXXXXXXXXXXXXXXXX"/>
		<add key="AudioFilesPath" value="audio"/>
		<add key="SupportedAudioFormat" value="flac|mp3|mpeg|wav"/>
		<add key="TextFilesPath" value="text"/>
	</appSettings>

Inside application path you will see 2 folders

1. audio - which is input to this application
2. text - which is output from this application

Many things to explore in this Speech to Text service, I just touched the very basic feature.

Kindly let me know if you have any suggestions.

Thank you.