Speech Input & Output
Our speech input and speech output capabilities power seamless voice interactions, transforming how users communicate with technology. Whether it's precise speech recognition or lifelike text-to-speech, our solutions create natural, intuitive voice experiences.
Together, these capabilities unlock the full potential of voice interaction – empowering natural communication between users and their vehicles, from seamless in-car dialogue to intuitive remote control.
Automatic Speech Recognition (ASR)
ASR converts speech into text, offering cloud, on-device, and hybrid deployment options for versatile speech processing across industries. Optimized for real-time accuracy, it supports 42 languages and adapts to complex use cases—from simple commands to AI-driven assistants.
User Benefits
Effortless Voice Interaction: Enables seamless recognition of diverse accents and dynamic vocabulary for accurate commands
Reliable Hands-Free Control: Works in noisy environments with barge-in functionality, allowing speech input while the system is mid-response
Expanded Access to Information: Connects with your favorite cloud services for real-time data retrieval, enhancing navigation, entertainment and daily assistance
OEM Benefits
Scalable Deployment: Supports a wide range of use cases from small vocabulary setups to integrations for complex automotive assistants
Industry Compliance: Ensures GDPR adherence while protecting user data, offering secure speech interactions
Optimized for Mobility: Designed for automotive and mobile use, delivering high-performance speech recognition beyond just vehicle applications
Exterior Vehicle Interaction (EVI)
Combining our expertise in exterior microphone placement with our in Audio AI, EVI allows for remote voice-control of a vehicle. It extends around a defined radius of the vehicle and is set up to identify only the voice of the user, listening for a specific wake-up word before activation.
User Benefits
Improved Convenience: Makes every-day experiences better – think opening the trunk with a voice command while hands are full of groceries or closing the sunroof from inside your home when rain is on the way
More Secure Vehicles: Enables drivers to lock their doors or close their windows using only their voice, making sure their belongings are safe inside
Easier Way to Pay: Lets drivers pay for things in the outside world using in-car commerce systems, authenticating purchases for gas or coffee while you’re outside the vehicle
OEM Benefits
Flexible Deployment: Compatible with a variety of exterior microphone setups and installation architectures—including those used for EVD
Competitive Differentiation: Delivers a standout driver experience by enabling novel, hands-free and convenient interactions outside the vehicle
Cost Efficiency: Extends on the existing speech interface, as simple software add-on or as stand-alone module, eliminating the need for additional external motion sensors
Voice Activation
(Just Talk, Wake-up Words & Open Channel)
Our voice activation technology enables seamless interactions with voice assistants through predefined and customizable wake-up words, AI-powered Just Talk, and Open Channel. Designed for effortless control, these solutions eliminate the need for manual activation while ensuring accurate speech detection in various environments.
User Benefits
Hands-Free Convenience: Allows users to activate assistants by voice instead of pressing buttons, enhancing usability
Smoother Interactions: Identifies relevant speech while filtering out unintended utterances for more effective voices assistant engagement
OEM Benefits
Customizable Setup: Expands setup flexibility by enabling OEMs to define custom activation words, allowing them to tailor the voice experience to their brand identity and design preferences
Flexible Integration: Supports embedded AI and Large Language Model (LLM)-based systems for adaptable deployment
Privacy-First Approach: Ensures compliance, including support for Android SoundTrigger HAL, with data protection rules while delivering a frictionless voice experience
Text-to-Speech (TTS)
TTS converts written text into natural, expressive and emotional voice output, supporting multiple languages and customizations for seamless brand integration. With deployment options across cloud and embedded platforms, it powers real-time, engaging speech interactions for automotive assistants, smart devices, and accessibility tools across 65+ languages.
User Benefits
Enhanced Accessibility: Makes digital content more inclusive with clear, expressive voice output
Safe Hands-Free Interaction: Optimized for situations where users are focused on other things, including enabling deployments of in-car voice assistants to reduce distracted driving
OEM Benefits
Customizable Voices: Supports a range of voice, emotion and reading styles for a personalized, brand-rich experience
Flexible Integration: Fully compatible with Cerence Speech Service and SDK for smooth deployment across platforms and able to support hybrid TTS solutions
Compliance Ready: Designed to meet GDPR and European Accessibility Act requirements for global scalability