← Back to Discover

Azure Text to speech

Microsoft's Azure Speech voice gallery for developers building apps that speak, with neural voices in many languages, usable from the cloud or a Docker container through an SDK and REST API.

Text to speechModel APIs
Visit website ↗

What it does

This page is the Voice Gallery of Speech Studio, part of Azure AI. It is a catalogue for developers who want applications and services that speak, offering neural voices that the page describes as expressive and humanlike, across many languages and variants. Examples are organised by use case. The voices can be used from the cloud or from a Docker container. The page links to documentation, sample code, an SDK reference and a REST API, and walks through creating a Speech resource and following a quickstart. Using the service requires an Azure account with a Speech or Cognitive Services resource. The page says the Voice Gallery is now also available in Azure AI Foundry, and that new Azure sign-ups can get a free 200 dollar Azure credit. It does not list text to speech prices.

Capabilities

  • Catalogue of neural voices across many languages and variants
  • Examples organised by use case
  • Available in the cloud or as a Docker container
  • SDK, REST API, documentation and sample code
  • Quickstart for creating a Speech resource

When to use it

  • You are building an app or service that needs spoken output
  • You want to browse and compare voices before choosing one
  • You already use Azure and want speech in the same account