Standard, WaveNet, Neural2, and Studio voices

Overview

Text-to-Speech creates raw audio data of natural, human speech. That is, it creates audio that sounds like a person talking. When you send a synthesis request to Text-to-Speech, you must specify a voice that 'speaks' the words.

There are a wide selection of voices available for you to pick from in Text-to-Speech. The voices differ by language, gender, and accent (for some languages). Some languages have multiple voices to choose from. See the Supported Voices page for a complete list of voices available in your language. You can tell Text-to-Speech to use a specific voice from this list by setting the VoiceSelectionParams fields when you send a request to the API. See the Text-to-Speech Quickstarts for details on how to send a synthesize request.

Neural2 voices

The Text-to-Speech API provides a premium voice tier called Neural2. Neural2 voices are based on the same technology used to create a Custom Voice. Neural2 represents the latest in synthetic voice generation and allows anyone to use Custom Voice technology without training their own custom voice. They're available in global and single region endpoints.


Example 1. Neural2 voice

Studio voices (Preview)

The Text-to-Speech API provides Studio voices. This voice type is designed specifically for use with long-form texts such as narration, news reading, and so on. Studio voices doesn't currently support SSML.


Example 1. The en-US-Studio-O voice reading the Great Gatsby.

Standard voices

The voices offered by Text-to-Speech differ in how they are produced, the synthetic speech technology used to create the machine model of the voice. One common speech technology, parametric text-to-speech, typically generates audio data by passing outputs through signal processing algorithms known as vocoders. Many of the standard voices available in Text-to-Speech use a variation of this technology.

WaveNet voices

The Text-to-Speech API also offers a group of premium voices generated using a WaveNet model, the same technology used to produce speech for Google Assistant, Google Search, and Google Translate. WaveNet technology provides more than just a series of synthetic voices: it represents a new way of creating synthetic speech.

A WaveNet generates speech that sounds more natural than other text-to-speech systems. It synthesizes speech with more human-like emphasis and inflection on syllables, phonemes, and words.

Chart shows WaveNet has highest preference by native speakers Figure 1. Chart showing comparison of WaveNet to other synthetic voices, human speech. The y-axis values represent the Mean Opinion Score (MOS) for each voice. Test subjects ranked each voice on a scale of 1-5 according to how much it sounded like natural speech. For more information on MOS scores and WaveNet technology, see the DeepMind WaveNet page.

Unlike most other text-to-speech systems, a WaveNet model creates raw audio waveforms from scratch. The model uses a neural network that has been trained using a large volume of speech samples. During training, the network extracts the underlying structure of the speech, such as which tones follow each other and what a realistic speech waveform looks like. When given a text input, the trained WaveNet model can generate the corresponding speech waveforms from scratch, one sample at a time, with up to 24,000 samples per second and seamless transitions between the individual sounds.

To hear the difference between a Wavenet-generated audio clip and a clip generated by another text-to-speech process, compare the two audio clips below.


Example 1. High quality, non-WaveNet voice


Example 2. WaveNet voice

Try it for yourself

If you're new to Google Cloud, create an account to evaluate how Text-to-Speech performs in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

Try Text-to-Speech free