To use the proprietary Azure Speech service you will need a free Azure subscription. This will allow, for example (as checked in May 2021), per monthly, 5 hours of audio transcription and 5 million character text to speech. See Azure Pricing and Azure Free Account to subscribe.
Once you have an account visit the Azure Portal to Create a Speech resource. Once created you can access the subscription key and the endpoint from the portal. These two details are required for your access to the service through the MLHub package. These will be asked for during the package configuration.
ml configure azspeech
The configuration will proceed with something like the following:
Private information is required to access this service. See the README for more details. Please paste your Azure subscription key: Please paste your Azure subscription location: westus That information has been saved into the file: /home/kayon/.mlhub/azspeech/private.json
Notice that the credentials are saved and will be utilised for each of the commands supported by the package.
Your donation will support ongoing availability and give you access to the PDF version of this book. Desktop Survival Guides include Data Science, GNU/Linux, and MLHub. Books available on Amazon include Data Mining with Rattle and Essentials of Data Science. Popular open source software includes rattle, wajig, and mlhub. Hosted by Togaware, a pioneer of free and open source software since 1984. Copyright © 1995-2022 Graham.Williams@togaware.com Creative Commons Attribution-ShareAlike 4.0