Azure AI Speech - Text to Speech

Azure > AI Services > Speech > Text to Speech

What is Text to Speech?

Text to Speech (TTS) allows you to convert text into natural-sounding speech. Azure AI Speech offers a robust TTS service with various voices, languages, and customization options. It's perfect for creating voice-enabled applications, accessibility features, and more.

Key Features

  • Multiple Voices: Choose from a diverse selection of voices in various languages and accents.
  • Custom Voice: Train a custom voice based on your own audio data.
  • Speech Synthesis Markup Language (SSML): Control pronunciation, pauses, and intonation using SSML.
  • Real-time Streaming: Receive speech output in real-time.
  • Endpoint-based Access: Integrate TTS into your applications using a secure endpoint.

Getting Started

Create an Azure Speech Service resource to begin.

Text to Speech Flow

Pricing

Pricing is based on usage. Review the Azure AI Speech pricing page for details.