Azure Text to Speech
Microsoft Azure cloud service for converting text to natural-sounding speech in more than 400 voices and 140 languages.
About
Azure Text to Speech is a cloud API from Microsoft that synthesizes spoken audio from text using neural voice models. It offers more than 400 prebuilt voices across over 140 languages and locales, with options to adjust speaking style, rate, pitch, and emphasis through Speech Synthesis Markup Language. A custom neural voice feature lets organizations train a branded voice from recorded samples. The service integrates with other Azure AI services and is commonly used for voice assistants, accessibility tools, e-learning narration, and call center automation. Pricing is consumption-based on characters converted, with a free tier available each month and standard and custom neural voice rates for higher volumes.