Acapela Group / Solutions

Acapela TTS for Linux Embedded

Software Development toolkit for Linux embedded based devices or applications.

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

Acapela TTS for Linux Embedded was designed to allow developers to integrate text to speech into any Linux Embedded device or application. Breathe life into your interface and content, provide users with the Voice First experience, let your applications talk with a wide range of pleasant and smart voices. 

Developer benefits

Simple integration of text to speech voices into your Linux Embedded application, for a natural interface and rich audio content in over 30 languages and 120 voices.

Simple API, the same as Windows Mobile.

Market apps and services

For smart toys, virtual assistants, portable Accessibility applications, IoT, robots, passenger, information systems, navigation, in-car voice assistants, blindness, visual impairments, talking book players, braille, BrailleNote, computer aids, reading aids, digital vision assistants, video magnifiers, and much more.

Key benefits

Two voice formats

Low Footprint (15-30MB/voice) and High Quality Medium (40-150MB/voice) for embedded text to speech, no internet connection needed.

Supported Devices

Acapela TTS for Linux Embedded supports ARM, MIPS and x86 and other compilations on request.

Audio control

Perfectly integrated with Windows Phone audio management possibilities.

Very natural and pleasant voices

Simple integration of text to speech voices for a natural interface and rich audio content, in over 30 languages and 120 voices.

Technical specifications

  • Supported default versions (static and dynamics lib)
    Most popular versions of arm, arm64, mips, x86, x86_64 processors are supported (for complete list, please contact us)
  • Other compilations
    eabi 5, Samsung Bada, Nokia MeeGo, other gnu gcc, and other platforms on request.
  • API
    Proprietary API (NSCAPI and babile).
  • Development Language
    C, C++.
  • Text tags
    to modify parameters on the fly.
  • High Quality Voices: Acapela TTS for Linux Embedded – HQ and HQ LF Unit Selection synthesizer technology
    • CPU usage : From 70 MIPS to 120 MIPS depending on the voice format.
    • Running memory needed: From 3-4 MB to 7-20 MB depending on the voice format.
    • Storage memory: 2 MB + voice data (from 10 MB to 200MB depending on the voice format).
    • >Audio Output : 8, 11, 16, 22 kHz.
  • Colibri Voices: Acapela TTS for Linux Embedded – Colibri HMM synthesizer technology
    • CPU usage : From 130 to 150 MIPS depending on the voice format.
    • Running memory needed: 3-4 MB.
    • Storage memory: 2 MB + voice data (from 3 to 9 MB depending on the voice).
    • Audio Output: 22 kHz.
  • Please contact us for more information.

Pricing information

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

  • The Software Development kit is a developer license (with libraries, sample code) and support and maintenance service. You pay a yearly fee.
  • The Commercial licence: When a product/application/service has been developed incorporating our software, a royalties-bearing agreement will be worked out. The level of royalties will depend on the number of units, on the voices and on the languages used.
Need more information for your voice project?
Book a demo