Wakeword

Enable intuitive, hands-free voice interaction by using one of our state-of-the-art, low-power keyword spotting offerings.

Enhance the smart home experience for your customers using a brand-wide wake phrase to control all devices in the home.
Give your customers the flexibility to control their devices using a variety of different wake phrases. Fluent.ai’s Alexa, Google, and Cortana WakeWord offerings can be combined together along with any other wake phrase of your choice to enhance the user experience.
Personalize your products with Fluent.ai’s User-Trainable WakeWord. Users can quickly and easily create their own WakeWord directly on the device with just three utterances.

Smart Home Devices

Wearables

Robotics

Wake up your voice-enabled device with one of our four low power keyword spotting solutions that beat the state of the art systems. Our patented Convolutional Neural Networks (CNN) technology-based wake phrase recognition systems enable incredibly low power and small footprint operations and provide low false accept and false reject rates even in far-field and noisy scenarios where conventional systems fail.

Minimum Device Requirements*

Solution

Single WakeWord
Multi-WakeWord (up to 4)
WakeWord + Speaker Recognition
  • RAM
  • Storage
  • Latency
  • Minimum Frequency
  • Recommended Platforms
  • 25 KB
  • 200 KB
  • 100 ms
  • 30 MHz
  • ARM Cortex M4 or higher
  • No increase in requirements
  • 30 KB
  • 300 KB
  • 100 ms
  • 30 MHz
  • ARM Cortex M4 or higher

*Note that these numbers are estimated on a particular CortexM4 platform. The exact footprint might change depending on your hardware, its features, and the support of various Fluent libraries for the hardware.

Minimum Device Requirements*

RAM

  • SINGLE WAKEWORD
    25 KB
  • MULTI-WAKEWORD
    25 KB
  • WAKEWORD + Speaker Recognition
    30 KB

Storage

  • SINGLE WAKEWORD
    200 KB
  • MULTI-WAKEWORD
    200 KB
  • WAKEWORD + Speaker Recognition
    300 KB

Latency

  • SINGLE WAKEWORD
    100 ms
  • MULTI-WAKEWORD
    100 ms
  • WAKEWORD + Speaker Recognition
    100 ms

Minimum Frequency

  • SINGLE WAKEWORD
    30 MHz
  • MULTI-WAKEWORD
    30 MHz
  • WAKEWORD + Speaker Recognition
    30 MHz

Recommended Platforms

  • SINGLE WAKEWORD
    ARM Cortex M4 or higher
  • MULTI-WAKEWORD
    ARM Cortex M4 or higher
  • WAKEWORD + Speaker Recognition
    ARM Cortex M4 or higher

*Note that these numbers are estimated on a particular CortexM4 platform. The exact footprint might change depending on your hardware, its features, and the support of various Fluent libraries for the hardware.

Universal Language & Accent Support

Fluent.ai’s unique Speech to Intent technology allows us to quickly develop speech recognition models in any language and for any accent on demand.

En NA

En UK

En AUS

Sp MEX

Sp ESP

Fr FRN

Pr BRA

De

Ko

It

Mn

Hr

Pl

Ru

Tr

Speaker Recognition

Fluent.ai offers industry-leading solutions for speaker recognition along with wake word recognition for personal devices. With Fluent Speaker Recognition, the device is able to recognize one among many users in shared usage scenarios and respond as per a user's personal preferences.

Fluent.ai is a leader in low-power speech understanding solutions. Our systems are highly portable and require a very light footprint. We support a wide range of hardware platforms. In particular, both our WakeWord and Core systems are able to run on ARM CortexTM M4 series of microcontrollers (without needing a Floating Point Compute Unit) from AmbiqMicroTM and STMicroelectronicsTM, ARM CortexTM M7 series, ARM Cortex A series of processors, and many digital signal processors (DSPs). We have also ported our algorithms to various AI-chips with specific neural network accelerators. Contact us if you have specific hardware requirements.

Supported
Hardware

Enhance your devices with Fluent.ai's
offline, robust and multilingual voice AI engine