NeoSpeech’s Text-to-Speech Engine SDK Overview
Ready to build a stand-alone text-to-speech product or application? Here’s everything you need to know.
This blog is part 1 of a 5-part blog series highlighting each of NeoSpeech’s text-to-speech solutions
If you’re building a custom text-to-speech application, or you want to give your product a voice, then you’ve come to the right place.
At NeoSpeech, we have a variety of solutions that can make that happen. Our product packages were optimized to make it easy for you to integrate our text-to-speech voices into your product. Plus, you can be assured that you’ll have the most natural sounding text-to-speech voices that your customers will love.
Here are all of NeoSpeech’s Solutions:
- VoiceText TTS Engine SDK
- VoiceText TTS Server SDK
- VoiceText Embedded SDK
- VoiceText SAPI
- VoiceText Editor (VT Editor)
For this blog, we’ll focus on NeoSpeech’s VoiceText TTS Engine SDK. The purpose of this blog (and the rest in this series) is to explain in more detail the purpose of each of our products, who they’re for, and what you can expect if you purchase them.
The VoiceText TTS Engine SDK is for developers wanting to build custom speech-enabled applications. That could mean an announcement system, a screen reader, or just an application for creating voice files.
So what exactly comes with this product package? And how does that work? Keep on reading to find all the answers and see if this is the right solution for you.
What is it?
This product, broken down into simplified terms, is really two things. First, there’s the text-to-speech engine. Second, there’s the SDK package. Let’s define what each one is.
This is our core technology. The engine is what is able to convert text into audible speech. The engine contains a database of all the broken-down and tagged units of speech from the original voice actor. When the TTS engine receives text, it analyzes it to understand the meaning of the text, then it pulls the necessary pieces of speech from the database and puts them together to generate the speech output.
You can read more about how our text-to-speech engines work here.
This stands for software development kit. This is a set of tools that allow you or your developer to integrate our text-to-speech engine into your custom product or application. These tools that we send you make the process of incorporating our technology into your own application much easier.
You can purchase just the VoiceText TTS Engine or you can purchase it with the SDK package. We recommend getting the SDK package if you are building a custom application.
Who is this solution for?
The VoiceText TTS Engine SDK is for building stand-alone applications on Windows and Linux operating systems. We can also customize our TTS engine to port it to another operating system if that is what you need.
(If your solution uses an embedded operating system, then you want our VoiceText Embedded SDK. If you’re using a server to host your TTS engine, get our VoiceText TTS Server SDK)
The key word here is “stand-alone”. This means that the application doesn’t have to connect to the internet or to another device/application to work. It works on its own.
To have a stand-alone TTS application, the text-to-speech engine must be stored within the application itself, or at least on the same computer that the application is running on.
So let’s say you’re building an application to create voice prompts for an announcement system. In this scenario, you just need one text-to-speech application to create and save the voice files. You would download our TTS engine and SDK packages, build your program, and then use it to make the voice files.
But what if your customers need to make their own voice prompts? Or their text-to-speech needs to be dynamic because their announcement systems will always say something different? In this case, you would need to include the full TTS engine in the announcement system application that you send to your customers so that they can have the ability to make their own voice prompts on the spot.
No matter how you do it, the most important thing to know about the VoiceText TTS Engine is you’re your custom application must be able to access the TTS engine locally.
If you’d rather store the TTS engine on a server that your end-users and customers would access to receive speech, then you need to look into our VoiceText TTS Server and Web Service products.
One of the pros of choosing the VoiceText TTS Engine over our sever-based solutions is that you’ll have the text-to-speech engine saved within your custom application, making it easier to access. A con could be that a TTS engine takes up a lot of memory, which would give your custom application a larger footprint.
Make sure to read about all of our products and solutions to make sure you find the best one for you. Or, you could always just get in touch with our friendly sales team and they’ll help you out.
How does NeoSpeech optimize it for my needs?
We don’t sell cookie-cutter versions of our product. Each package is customized to fit our customer’s needs.
As we just mentioned, there are a couple operating systems that our engine can run on. We can also custom port our engine if it runs on an operating system that we currently don’t support.
We also let you choose which sampling rate you want your audio in. Anything from 8 kHz, 16 kHz, 22kHz, and 44kHz. The higher the sampling rate, the higher the voice quality will be.
On the flip side of that, the higher the sampling rate, the higher the footprint will be too. Our packages can be anywhere between 3 MB to 1.5 GB.
You’ll have to choose which sampling rate and footprint size are best for you based on your needs. Is having a small footprint or higher voice quality more important? It depends on your application.
Finally, we have dozens of different voices and languages to choose from!
How does it work?
Here’s everything you need to know about how to purchase, install, and use our TTS engine and SDK.
To purchase our VoiceText TTS Engine SDK, you have to get in touch with us through our Sales Inquiry form. Once we receive your inquiry, one of our sales team members will get in touch with you and discuss the details of your project.
We do this so we can understand everything about your business and your product. This allows us to make sure we optimize the TTS engine to your specifications.
Once you have purchased our VoiceText TTS Engine SDK, we’ll send you the download files for both the TTS engine and the SDK package.
Once you have downloaded both files, our engine and SDK package should be stored on your computer. Here is what the file folder would look like for the TTS engine and SDK package:
The example above is for Julie’s (US English) engine and SDK package for a Windows operating system. The “bin”, “data-common”, and “data-julie” folders are part of the TTS engine. The “docs”, “include”, “lib”, and “samples” folders are part of the SDK package.
We’ll go into what each folder contains later.
In same email, we’ll also send you the license key, or CD key, along with a set of instructions on how to use the license key to verify your text-to-speech engine.
Basically, you just need to use the license key to get a verification file that you’ll then save in one of your TTS engine file folders. This will verify your copy of our software and give you full access to our TTS engine!
At this point, you should have the text-to-speech engine ready and all the SDK tools you need, so it’s time to start building and integrating!
Here’s an overview of what files come with the VoiceText TTS Engine SDK so you’ll know what to do with them:
- bin – If you’re on a Windows operating system, this file contains a couple applications you can operate. The first will be a VT Editor of the voice you purchased so you can use it and test the voice yourself. The other is a dictionary application that lets you modify and change the way certain words or phrases are pronounced.
- data-common – This folder holds the dictionary file. This is an excel document that contains all the changes and special rules you’ve put in place. You can put as many different dictionaries in this folder as you want! This folder also contains the license folder which we’ll explain more later.
- data-(name) – This folder is the database. This is essentially where the text-to-speech voice lives.
- docs – Here you’ll find the SDK user manual. This manual will teach you everything you need to know about how to use our TTS engine and how to integrate it with your custom application.
- include –This folder has the header library source file.
- lib – This folder has the second library source file.
- samples – In here you’ll find some sample script to see how the SDK is used.
When integrating, all you need to do is import both library source files (header and lib) into your application, and then write code that tells your program where the database file is located so it can be accessed. From there you just need to write the code that’ll tell your application when and how to use the TTS engine! Simple as that.
Hopefully this brief overview of our VoiceText TTS Engine SDK gave you a better idea of what you can expect with this solution and if it’s for you. Keep in mind that whenever you purchase a solution from NeoSpeech we’ll send you all the detailed manuals you’d need to build your product or application.
If you believe that this product is for you, or if you have any questions, get in contact with our sales team now!
Feel free to ask us any questions about the VoiceText TTS Engine SDK in the comments below and we’ll be sure to answer them. And be on the lookout for the rest of the articles in this series!
Learn More about NeoSpeech’s Text-to-Speech
Want to learn more about all the ways Text-to-Speech can be used? Visit our Text-to-Speech Areas of Application page. And check out our Text-to-Speech Products page to find the right package for any device or application.
If you’re interested in integrating Text-to-Speech technology into your product, please fill out our short Sales Inquiry form and we’ll get you all the information and tools you need.