Please refer to the Setting up a rest client section from Chapter 3, Cloud Vision API, to set up a REST API client, either Postman or cURL, before you continue. Now that we have all the required setup done, let's get started with exploring the API. In this section, we are going to upload a single channel, Linear16 encoded, with a 44100 sample rate, in base64 format, to Cloud Speech API and get its transcription. There are three ways we can convert audio to text using the Cloud Speech API:

• Synchronous speech recognition
• Asynchronous speech recognition
• Streaming speech recognition