Acapela Group / Solutions

Acapela TTS for Linux Server

Software Development toolkit designed to give a voice to your telephony and Linux server-based services.

Deliver 24/7 real-time vocal information to your customers

Acapela TTS for Linux Server has been designed to speech enable in real time all sorts of telecommunications applications and server-based services.

Latest innovation in voice AI with Acapela DNN opened a new era for voice creation and its uses, enabling the creation of voices perfectly adapted to the specific requirements of a company, a brand or a device.

Developer benefits: Acapela TTS for Linux Server targets telecom and server-based applications, from single host solutions to distributed architectures. Scalable and client-server architecture. 

Market apps and services: for voice assistants, IoT, contact centers, IVR, CRM, notification systems, ATM vocal assistants, passenger information, navigation, web-reading, audio books, audio production, simulation and training, e-learning, serious gaming, etc.

Key benefits

Client-server architecture

Designed for network telecom applications, from single host solutions to distributed architectures.

High Density performance

Efficient TTS server, offering lower hardware investment with maximum efficiency.

Scalability and multi-processor

Multi-channel engine, optimized for mono and multi-processor systems.

Reliable and manageable

Designed to run 24/7, remotely administrable.

Standard Compliance

Can be used as a TTS resource in any Voice XML platform with the IETF MRCP v2 protocol layer and the support of W3C SSML.

Technical Specifications

  • Voice AI
    Support of neural voices*
  • Online License Manager
    Powerful online license manager for a better management of your usage
  • Server
    • OS: RedHat Enterprise or CentOS 7, Debian 9 and higher
    • Running mode: Remote (IP), as a desktop process or as a service
    • Compatible with Linux or Windows client
  • Client
    • OS: RedHat Enterprise or CentOS 7, Debian 9 and higher
    • Compatible with Linux or Windows server / Can work locally
  • Text input
    • Text input: Unlimited vocabulary, raw text, phonetic input, SSML support, tags
    • Text normalization: dates, time, currencies, units, URL/emails, abbreviations and exceptions.
  • API and Programing language
    • Proprietary API
    • C/C++, Java
    • Support MRCP V2
  • Audio format
    • 8 kHz telephony modes / 22 kHz PCM mode
    • buffer, streaming or file generation
  • Tools
    Lexicon editor / Demo sample / Web monitor / Test tools
  • * Recommended minimum technical requirements apply, please contact us.

Pricing info

The Acapela TTS for Linux Server offer consists of two parts:

SDK:

• The Software Development Kit is a developer license (with libraries, sample code) and support and maintenance service for the first year.
• You pay a once only fee

Commercial Licence:

• When the text to speech is used in live mode, the price of the licence reflects the maximum of concurrent users and the number of languages activated.
• When the text to speech is used for audio production (creation of audio files used several times), the price is based on prepaid packages of speech hours.

• Please note: there is a yearly fee for the support and maintenance service.

Need more information for your voice project?
Book a demo