Go to Menu

VoiceText Server

Outstanding speech output for IVR, emergency alert systems and more.

Contact Us

Flexible client-server solutions for effortlessly and seamlessly deploying and controlling high-quality ReadSpeaker TTS voices in your standards-based telephony and IVR systems.

VoiceText Server enables flawless dynamic multithreaded speech sessions. Integrate ReadSpeaker synthetic voices in your client-server architecture and run your intelligent voice services efficiently.

Optimize your server-based applications with VoiceText Server.

Take your services and applications to the next level: manage multi-threaded, multiple voice TTS requests for IVR and emergency alert systems, mobile devices, and more with VoiceText Server.

Effortlessly and seamlessly integrate ReadSpeaker voices into your client-server architecture and run your application efficiently, interacting with VoiceText Server through a command line tool, REST API or TCP/IP communication protocol (Linux Only). Includes pronunciation lexicon tool and documentation.

Features

Web Admin Control Panel

Access the control panel wherever you are. Sign in to manage all the settings. Adjust the pitch, volume, speed, and pause. Enable and disable voice engines. Set maximum channels and more using the user-friendly web interface.

Monitor Thread Usage in Real Time

No need to wait—track simultaneous speech synthesis occurring in real-time and over time on a live graph.

Operating System and API Compatibility

Choose what works best for you—Windows or Linux. Integrating VoiceText Server into your application is easy and straightforward. Our server is designed to support all major APIs, including: Command Line Interface, REST web API, C-based APIs, Java, .NET.

A choice of high-quality footprints

Depending on the level of definition you want to deploy in you application, our high-quality footprints range between 5MB and 2GB per voice.

A variety of audio formats and sampling rates

We support the following audio formats and sampling rates: PCM, Wav, Ogg and MP3* (*using third party library) –  8KHz or 16KHz.

Incremental Reporting

Break down your customers’ usage by speech requests, text length, response time from the server and more—and see how this data compares to usage over the past hour, day, week, or three months ago. VoiceText Server automatically generates a log file every 15 minutes, so you see what caused a traffic spike and when it occurred.

System requirements

OS

Windows Server 2008 and higher, Linux RHEL 5 or higher, Ubuntu

CPU

8KHz or 16KHz

RAM

2 GB*
(*depending on number of channels)

Voice Footprint

5MB to 2GB per voice