In a weblog put up at this time Scott Low, Program Manager for the Microsoft Edge browser, introduced that starting with the latest Dev and Canary channel releases, preview builds of Microsoft Edge now embody assist for 24 cloud-powered textual content to speech voices throughout 21 completely different locales.
The first place these voices will present up is in Read Aloud, a function from the present (EdgeHTML-based) model of Microsoft Edge that provides folks the choice to have web sites learn to them by the browser.
The new voices are powered by Microsoft’s Cognitive Services and are anticipated to sound significantly better than the present robotic and unnatural voices.
The new voices come in two completely different types and could be distinguished from different voices you’ll have put in in your laptop by the truth that they’ve “Microsoft <voiceName> Online” of their names:
Neural voices – Powered by deep neural networks, these voices are essentially the most pure sounding voices out there at this time. Standard voices – These voices are the customary on-line voices provided by Microsoft Cognitive Services. Voices with “24kbps” of their title will sound clearer in comparison with different customary voices as a result of their improved audio bitrate.
To check out the brand new array of cloud-powered voices use the Read Aloud function. To do that, navigate to a web site, choose some textual content, proper click on it, and choose “Read aloud selection”. This will begin Read Aloud and also will open the Read Aloud menu bar which helps you to decide completely different voices and regulate studying velocity by clicking on the “Voice options” button:
It’s additionally price noting that these voices have been uncovered to builders via the JavaScript SpeechSynthesis API. This signifies that any web-based textual content to speech utility can leverage them to create extra configurable and human-sounding experiences within the new model of Microsoft Edge.
