Azure Speech documentation

Speech to text

• Get started with speech to text
• Real-time transcription
• Fast transcription
• Batch transcription
• Custom speech-to-text models
• More

Text to speech

• Get started with text to speech
• Improve synthesis with SSML
• Create a custom voice
• Make text to speech sound natural
• More

Voice Live

• What is Voice Live?
• Get started with Voice Live models
• Get started with Voice Live in Foundry agents
• Customize Voice Live

Tools

• Speech MCP tool in Microsoft Foundry
• About Speech Studio
• About the Speech CLI

Speech translation

• About speech translation
• Get started with speech translation

Scenario deep dives

• Captioning with speech to text
• Call center overview
• Pronunciation assessment

Hosting

• Azure Speech containers
• Azure Speech containers with Kubernetes
• Azure Speech containers on Azure Container Instances

Migration

• Migrate to speech-to-text REST API version 2025-10-15
• Migrate to the batch synthesis REST API

Voice Live SDK

Build low-latency speech-to-speech voice agents.

• C#
• Python
• Java (Preview)
• JavaScript (Preview)
• About the Voice Live SDK

Speech Transcription SDK

Develop high-quality transcription applications.

• Java
• Python
• About the Speech Transcription SDK

REST APIs

• Speech to text
• Batch transcription
• Text to speech
• Custom voice
• Batch synthesis
• Batch avatar

Resources

• Pricing
• Regions
• Learn

Support

• Support and help
• GitHub issues