Introducing the Unity Text-to-Speech Plugin from ReadSpeaker

As a game developer, how will you use text to speech (TTS)?

We’ve only begun to discover what this tool can do in the hands of creators. What we do know is that TTS can solve tough development problems, that it’s a cornerstone of accessibility, and that it’s a key component of dynamic AI-enhanced characters: NPCs that carry on original conversations with players.

There have traditionally been a few technical roadblocks between TTS and the game studio: Devs find it cumbersome to create and import TTS sound files through an external TTS engine. Some TTS speech labors under perceptible latency, making it unsuitable for in-game audio. And an unintegrated TTS engine creates a whole new layer of project management, threatening already drum-tight production schedules.

What devs need is a latency-free TTS tool they can use independently, without leaving the game engine—and that’s exactly what you get with ReadSpeaker AI’s Unity text-to-speech plugin.

ReadSpeaker AI’s Unity Text-to-Speech Plugin

ReadSpeaker AI offers a market-ready TTS plugin for Unity and Unreal Engine, and will work with studios to provide APIs for other game engines. For now, though, we’ll confine our discussion to Unity, which claims nearly 65% of the game development engine market. ReadSpeaker AI’s TTS plugin is an easy-to-install tool that allows devs to create and manipulate synthetic speech directly in Unity: no file management, no swapping between interfaces, and a deep library of rich, lifelike TTS voices. ReadSpeaker AI uses deep neural networks (DNN) to create AI-powered TTS voices of the highest quality, complete with industry-leading pronunciation thanks to custom pronunciation dictionaries and linguist support.

With this neural TTS at their fingertips, developers can improve the game development process—and the player’s experience—limited only by their creativity. So far, we’ve identified four powerful uses for a TTS game engine plugin. These include:

1. User interface (UI) narration for accessibility. User interface narration is an accessibility feature that remediates barriers for players with vision impairments and other disabilities; TTS makes it easy to implement. Even before ReadSpeaker AI released the Unity plugin, The Last of Us Part 2 (released in 2018) used ReadSpeaker TTS for its UI narration feature. A triple-A studio like Naughty Dog can take the time to generate TTS files outside the game engine; those files were ultimately shipped on the game disc. That solution might not work ideally for digital games or independent studios, but a TTS game engine plugin will.
2. Prototyping dialogue at early stages of development. Don’t wait until you’ve got a voice actor in the studio to find out your script doesn’t flow perfectly. The Unity TTS plugin allows developers to draft scenes within the engine, tweaking lines and pacing to get the plan perfect before the recording studio’s clock starts running.
3. Instant audio narration for in-game text chat. Unity speech synthesis from ReadSpeaker AI renders audio instantly at runtime, through a speech engine embedded in the game files, so it’s ideal for narrating chat messages instantly. This is another powerful accessibility tool—one that’s now required for online multiplayer games in the U.S., according to the 21st Century Communications and Video Accessibility Act (CVAA). But it’s also great for players who simply prefer to listen rather than read in the heat of action.
4. Lifelike speech for AI NPCs and procedurally generated text. Natural language processing allows software to understand human speech and create original, relevant responses. Only TTS can make these conversational voicebots—which is essentially what AI NPCs are—speak out loud. Besides, AI NPCs are just one use of procedurally generated speech in video games. What are the others? You decide. Game designers are artists, and dynamic, runtime TTS from ReadSpeaker AI is a whole new palette.

ReadSpeaker AI brings more than 20 years of experience in TTS, with a focus on performance. That expertise helped us develop an embedded TTS engine that renders audio on the player’s machine, eliminating latency. We also offer more than 90 top-quality voices in over 30 languages, plus SSML support so you can control expression precisely. These capabilities set ReadSpeaker AI apart from the crowd. Curious? Keep reading for a real-world example.

ReadSpeaker AI Speech Synthesis in Action

Soft Leaf Studios used ReadSpeaker AI’s Unity text-to-speech plugin for scene prototyping and UI and story narration for its highly accessible game, in development at publication time, Stories of Blossom. Check out this video to see how it works:

“Without a TTS plugin like this, we would be left guessing what audio samples we would need to generate, and how they would play back,” Conor Bradley, Stories of Blossom lead developer, told ReadSpeaker AI. “The plugin allows us to experiment without the need to lock our decisions, which is a very powerful tool to have the privilege to use.”

This example begs the question every game developer will soon be asking themselves, a variation on the question we started with: What could a Unity text-to-speech plugin do for your next release? Reach out to start the conversation.