Speech-to-Text Transcription

Audio Toolbox™ enables you to interface with third-party speech-to-text APIs from MATLAB^®.

To interface with third-party speech-to-text APIs, you must have the following:

• Audio Toolbox release R2017a or above

• Audio Toolbox extended functionality available from File Exchange

• One of the following APIs:

  • Google^® Speech API

  • IBM^® Watson Speech API

  • Microsoft^® Azure Speech API

The third-party APIs require you to generate keys for identification purposes. To begin, download the extended Audio Toolbox functionality from File Exchange. The File Exchange submission includes a tutorial to get you started. Once you have installed the speech-to-text functionality and set up your API keys, you can perform speech-to-text transcription programmatically or using the Signal Labeler app.