Text-to-Speech documentation

Text-to-Speech documentation

Overview

Text-to-Speech converts text or Speech Synthesis Markup Language (SSML) input into audio data of natural human speech. Learn more

Guides

• Quickstart: Use the command line

• Quickstart: Use the client libraries

• Create voice audio files

• Decode base64-encoded audio content

• List all supported voices

• Specify regional endpoints

• Use device profiles for generated audio

• More  

Reference

• Supported voices and languages

• Speech Synthesis Markup Language (SSML)

• Text-to-Speech Client Libraries

• REST API

• RPC API

• More  

Resources

• Pricing

• Quotas & limits

• Release notes

• Getting support

• Billing questions

• More  

Try Text-to-Speech for yourself

Create an account to evaluate how our products perform in real-world scenarios.
New customers also get $300 in free credits to run, test, and deploy workloads.

Try Text-to-Speech free