Get an inside look at new AI & ML capabilities to help you make smarter decisions. Register for Next '21.

Jump to

Text-to-Speech

Convert text into natural-sounding speech using an API powered by Google’s AI technologies.
  • action/check_circle_24px Created with Sketch.

    Improve customer interactions with intelligent, lifelike responses

  • action/check_circle_24px Created with Sketch.

    Engage users with voice user interface in your devices and applications

  • action/check_circle_24px Created with Sketch.

    Personalize your communication based on user preference of voice and language

Benefits

High fidelity speech

Deploy Google’s groundbreaking technologies to generate speech with humanlike intonation. Built based on DeepMind’s speech synthesis expertise, the API delivers voices that are near human quality.

Widest voice selection

Choose from a set of 220+ voices across 40+ languages and variants, including Mandarin, Hindi, Spanish, Arabic, Russian, and more. Pick the voice that works best for your user and application.

One-of-a-kind voice

Create a unique voice to represent your brand across all your customer touchpoints, instead of using a common voice shared with other organizations.

Demo

Put Text-to-Speech into action

Type what you want, select a language then click “Speak It” to hear.

Key features

Key features

Custom Voice (beta)

Train a custom voice model using your own audio recordings to create a unique and more natural sounding voice for your organization. You can define and choose the voice profile that suits your organization and quickly adjust to changes in voice needs without needing to record new phrases.

WaveNet voices

Take advantage of 90+ WaveNet voices built based on DeepMind’s groundbreaking research to generate speech that significantly closes the gap with human performance.

Voice tuning

Personalize the pitch of your selected voice, up to 20 semitones more or less from the default. Adjust your speaking rate to be 4x faster or slower than the normal rate.

Text and SSML support

Customize your speech with SSML tags that allow you to add pauses, numbers, date and time formatting, and other pronunciation instructions.

View all features

What’s new

What's new

Sign up for Google Cloud newsletters to receive product updates, event information, special offers, and more.

Documentation

Documentation

Google Cloud Basics
Text-to-Speech basics

A guide to the fundamental concepts of using the Text-to-Speech API.

Quickstart
Quickstart: Using the command line

Set up your Google Cloud project and authorization and make a request for Text-to-Speech to create audio from text.

Google Cloud Basics
Supported voices and languages

Browse guides and resources for this product.

Google Cloud Basics
Custom Voice (beta) overview

Learn how you can create a unique and more natural-sounding voice with Custom Voice using your own studio-quality audio recordings.

Tutorial
WaveNet and other synthetic voices

Learn about the different synthetic voices available for use in Text-to-Speech, including the premium WaveNet voices.

Tutorial
Speaking addresses with SSML

This tutorial demonstrates how to use Speech Synthesis Markup Language (SSML) to speak a text file of addresses.

Use cases

Use cases

Use case
Voicebots in contact centers

Deliver a better voice experience for customer service with voicebots on Dialogflow that dynamically generate speech, instead of playing static, pre-recorded audio. Engage with high-quality synthesized voices that give callers a sense of familiarity and personalization.

Voice bots in contact centers reference architecture
Use case
Voice generation in devices

Enable natural communications with your users by empowering your devices to speak humanlike voices as a text reader. Build an end-to-end voice user interface together with Speech-to-Text and Natural Language to improve user experience with easy and engaging interactions.

Voice generation in devices reference architecture
Use case
Accessible EPGs (Electronic Program Guides)

Easily have the EPGs read text aloud to provide a better user experience to your customers and meet accessibility requirements for your services and applications. Try the EPG demo.

Easily implement text-to-speech functionality in EPGs to provide a better user experience to your customers and meet accessibility requirements for your services and applications. 

Reference architecture showing how TTS API can create accessible EPGs

All features

All features

Custom Voice (beta) Train a custom speech synthesis model using your own audio recordings to create a unique and more natural-sounding voice for your organization. You can define and choose the voice profile that suits your organization and quickly adjust to changes in voice needs without needing to record new phrases. Learn more.
Voice and language selection Choose from an extensive selection of 220+ voices across 40+ languages and variants, with more to come soon.
WaveNet voices Take advantage of 90+ WaveNet voices built based on DeepMind’s groundbreaking research to generate speech that significantly closes the gap with human performance.
Text and SSML support Customize your speech with SSML tags that allow you to add pauses, numbers, date and time formatting, and other pronunciation instructions.
Pitch tuning Personalize the pitch of your selected voice, up to 20 semitones more or less than the default.
Speaking rate tuning Adjust your speaking rate to be 4x faster or slower than the normal rate.
Volume gain control Increase the volume of the output by up to 16db or decrease the volume up to -96db.
Integrated REST and gRPC APIs Easily integrate with any application or device that can send a REST or gRPC request including phones, PCs, tablets, and IoT devices (e.g., cars, TVs, speakers).
Audio format flexibility Convert text to MP3, Linear16, OGG Opus, and a number of other audio formats.
Audio profiles Optimize for the type of speaker from which your speech is intended to play, such as headphones or phone lines.

Pricing

Pricing

Text-to-Speech is priced based on the number of characters sent to the service to be synthesized into audio each month. The first 1 million characters for WaveNet voices are free each month. For Standard (non-WaveNet) voices, the first 4 million characters are free each month. After the free tier has been reached, Text-to-Speech is priced per 1 million characters of text processed.

If you pay in a currency other than USD, the prices listed in your currency on Google Cloud SKUs apply.