• Nuance ist für Sie da
  • Support
  • Shop

VoCon Hybrid

Embedded and connected speech recognition

VoCon® Hybrid is a feature-rich SDK that provides superior functionality, unmatched accuracy, and high performance for a variety of applications that utilize speech control.

Proven across industries

The VoCon® product family has delivered the power of speech to consumer and industrial products for over 10 years.

Enhanced experience

VoCon Hybrid delivers a new level of speaker independent and continuous speech recognition, and multi-lingual language understanding.

Total hybrid solution

Full range of embedded and connected speech recognition services from embedded digit recognition to connected dictation and complex search functionality. Embedded failsafe for many use cases if network connectivity is lost.

Highly compatible

VoCon Hybrid can be combined with other solutions in the VoCon product family or Vocalizer's text-to-speech for a more robust speech dialog solution and improved accuracy.

VoCon Hybrid applications


VoCon Hybrid is the core speech recognition technology for Dragon Drive, a voice-powered application that provides a driver-centric connected car experience.

Learn more about Dragon Drive


VoCon Hybrid technology is used in screen readers and other products that provide access to information for the visually impaired.

Learn about solutions for accessibility

Consumer electronics

VoCon Hybrid enables voice control in a range of products including TVs, games and toys, language learning software, and mobile phones.

Learn about consumer devices solutions


VoCon Hybrid is used in a wide variety of industrial applications in warehousing and distribution equipment as well as medical equipment.

User experience

High accuracy in noisy environments
VoCon Hybrid is developed for mobile applications with high accuracy operation to SNR levels as low as 5dB.

Natural language understanding (NLU)
Recognizes natural speech, eliminating restriction to predefined commands for all VoCon Hybrid languages.

All inclusive main menu (a1M)
Enables all commands to be spoken in a single utterance on the main menu.

Extensive global language portfolio
Worldwide support for over 30 languages provides universal functionality.

Large vocabulary support
Enables embedded recognition for large lists with connected dictation and search capabilities.

Wake-up word
Always listening mode allows the user to “wake up” or activate their system with a keyword, like “Hello Dragon.” Removes the need for a “press to talk” button.

Talk over barge-in allows user to speak over spoken dialog prompts and be recognized.

Large related list support
Enables recognition from combined large lists recognizing only valid combinations, e.g. street + city + state for all USA, or part + warehouse combinations.

Flexible phone book selection
Recognizes partial contact names for multi-lingual phonebooks.

Spelling module
Spelling module available as backup to whole word recognition.

Bandwidth extension for 8kHz signals
Whenever 8kHz audio input is the only available format, like Bluetooth, it is now possible to recognize 8kHz audio input with standard 16kHz acoustic models.

Hardware acceleration
Supports Spansion and Neon Expansions to improve the operation point of the speech recognition both in speed and accuracy by shifting a part of the algorithmic processing to dedicated hardware.

Fuzzy match technology for POI search
Recognizes every possible word in a database in every possible order and permutations, including partial utterances. This search algorithm is especially useful when the user does not know the exact wording of the content he or she is searching for.

Software Development Kits (SDK)

VoCon® Hybrid Engine

Gain exceptional recognition accuracy tuned for noisy automotive environments. VoCon Hybrid Engine delivers a superior user experience and high acceptance rates across a wide variety of in-vehicle systems and applications. Continuous improvements of the speech algorithms ensure highest accuracy standards even for large and complex tasks.

VoCon® Hybrid Software Development Kit

Adds speech recognition functionality to any application. Includes VoCon® Hybrid speech recognition engine, a robust set of development tools, guides, and sample code that allow developers to build a high-quality speech-enabled application with optimum speed and efficiency.

VoCon Hybrid SDK is available in two variants that use the same API:

Basic SDK
Provides Nuance's state-of-the-art VoCon technology for embedded speech recognition and voice barge-in. This is recommended for embedded only applications with no requirement for connected speech recognition while having the flexibility to add connected speech recognition later.

Connected SDK
Provides access to Nuance's Dragon connected speech services in the network in addition to state-of-the-art VoCon technology for embedded speech recognition and voice barge-in. Connected services are available through the NDEV community powered by Dragon.

Platform support

Scalable, modular architecture

Supports a range of operating points so that smaller applications are not affected by higher CPU & RAM required for larger applications.

VoCon Hybrid supports:
  • Android
  • iOS (iPhone)
  • Linux (Ubuntu), (PC & ARM)
  • Windows XP & Windows 7 operating systems

The software interface in the Windows SDK is identical to the interface once ported to an embedded platform allowing code built on the PC to be reused on the platform.

Additional speech solutions

VoCon® Music Premium Add-On
Nuance in partnership with Gracenote, provides the capability to retrieve precompiled and editorially checked phonetics for artist and album names, alternative names and/or artist nicknames from regularly updated dictionaries. VoCon Music Premium requires VoCon Hybrid (Base) on platform and can be used with ASR & TTS solutions.

Vocalizer Expressive
Text-to-speech solution that enriches the user experience with enhanced expressivity by generating high quality and natural sounding speech.

Learn more

VoCon® Speech Signal Enhancement (SSE)
A suite of technologies that work together to remove noise from microphone input and send out a cleaner signal.

Learn more

Contact us to see how VoCon Hybrid and other Nuance technologies can provide a custom voice recognition solution designed around your needs.

Engage us
   Deutschland & Österreich

Choose your country.