Alexa > Solution Providers > Qualified AVS Solutions
Qualified solutions for the Alexa Voice Service (AVS) are complete reference solutions for creating products with Alexa built-in. They include chipsets, voice processing technologies, and client software that leverages the AVS APIs to help you easily build commercial-grade, voice-forward products while reducing development costs and accelerating the integration process.
Shensilicon 2-Mic Solution
A DSP Audio Front End development kit powered by Shensilicon with AISpeech's audio processing algorithms. The development kit supports 2-mic arrays, direction of arrival, noise suppression, reverberation cancellation, and echo cancellation, targeted at Alexa built-in smart speakers, tablets and TVs.
- Far-field
- 2-mic
- Voice-initiated
Cirrus Logic Voice Capture Solution
For portable speakers and compact audio device; uses Cirrus Logic audio algorithms.
- Far-field
- 2-mic
- Voice-initiated
DSP Group HDClear 3-Mic Solution
Enables low-power wake-on-voice operation and far-field voice recognition performance with only three mics.
- Far-field
- 3-mic
- Voice-initiated
Synaptics AudioSmart 2-Mic Solution
Low-power, far-field voice recognition with customizable microphone array spacing and orientation options.
- Far-field
- 2-mic
- Voice-initiated
XMOS VocalFusion 2-Mic (XVF3510) Solution
Powered by XMOS voice algorithms, the 2-mic XVF3510 is a BOM-efficient solution optimized for smart TVs and set-top boxes with Alexa built-in. It features an adaptive delay estimator to ensure audio-visual sync and stereo acoustic echo cancellation for barge-in support.
- Far-field
- 2-mic
- Voice-initiated
NationalChip 2-Mic Solution
Powered by Nationalchip AI-Labs, this solution is based on GX8008C with 2-mic voice pre-processing technologies and supports beamforming, noise reduction, and stereo acoustic echo cancellation. The solution is optimized for TVs, IOT, smart speakers and tablets.
- Far-field
- 2-mic
- Voice-initiated
AIspeech Software AFE
Software AFE development kit powered by AISpeech's audio processing algorithms. The development kit supports 4-mic & 2-mic arrays, direction of arrival, noise suppression, reverberation cancellation, and echo cancellation for creating products with Alexa Built-In.
- Far-field
- 2-mic linear & 4-mic linear
Bolom BoVoice™ Software AFE
Software AFE development kit powered by Bolom BoVoice speech processing algorithms. Development kit supports far-field beamforming, noise reduction and acoustic echo cancellation, with 2 and 4 microphone array configurations for creating Alexa Built-in products.
- Far-field
- 2-mic-linear and 4-mic-circular
Philips BeClear-SHF far-field Software AFE
Software AFE powered by Philips BeClear audio processing algorithms. BeClear SHF supports Multiple mic arrays, Multiple beams, Multichannel AEC and Direction of Arrival.
- Far-field
- 2-mic-linear, 4-mic-circular, 4-mic-linear
DSP Concepts TalkTo™ Software AFE
Software AFE offering unmatched voice performance in noisy environments, custom array support, integrated speaker processing, and extensibility with AudioWeaver. TalkTo includes an Adaptive Interference Canceller™ (AIC), Mono, Stereo, and Multichannel AEC (up to 7 channels), and Dynamic Beam-steering.
- Far-field, Near-field, Close-Talk
- 2-mic, 4-mic, 6-mic, and custom configurations
Horizon Windsper Computer Audition Solution
Software AFE development kit powered by Horizon's 2-mic speech processing algorithms. Windsper supports far-field voice interaction and high-quality stereo acoustic echo cancellation, and is optimized for Smart Home, in-car applications, and portable devices.
- Far-field
- 2-mic-linear
SoundAI SoundPi Cube Solution
Software AFE development kit that enables developers to test various algorithm interfaces, localize sound sources, and operate noise reduction processing for a wide range of device types and form factors.
- Far-field
- 2-mic-linear and 4-mic-linear configurations
Espressif's Audio Front-End Algorithms
Developed by Espressif AI-Labs, Espressif's Audio Front-End Algorithms suite supports 2-mic array, echo cancellation, blind source separation, channel selection to create best in class performance Alexa Built-In products.
- Far-field
- 2-mic linear
Knowles AISonic SmartMic Headset Solution
Alexa Mobile Accessory enabled solution for voice-initiated low-power Bluetooth headphones, headsets, and earbuds.
- Close-Talk
- 1-mic
- Voice-initiated
QuickLogic QuickFeather Solution
Close-talk smart hearable reference design for battery-powered applications.
- Close-Talk
- 2-mic
- Voice-initiated
CEVA ClearVox and WhisPro Software 6-Mic AFE Solution
Complete software AFE solution comprised of CEVA’s ClearVox audio front-end with CEVA’s WhisPro speech recognition package, providing high quality user experience for Alexa enabled devices in noisy environments. ClearVox supports various microphone configurations, speaker direction of arrival, beamforming, and mono/stereo acoustic echo cancellation, while WhisPro provides a neural network-based wake-word, with customizable voice commands and biometrics.
- Far-field
- 6-mic circular
- Voice-initiated
Qualcomm Smart Audio 400 Platform Solution
Comprehensive hardware and software development kit with the necessary building blocks to create smart speakers and smart home assistants with Alexa built-in.
- Far-field
- 2-mic and 4-mic configurations
- Voice-initiated
Amlogic A113X1 Far-Field Solution
Configurable for multiple mic arrays. An SoC with performance, low power consumption, and support for displays.
- Far-field
- 2-mic, 4-mic, and 6-mic configurations
- Voice-initiated
Allwinner SoC-Only 3-Mic Far-Field Solution
A cost-effective solution for integrating Alexa into devices with displays, and delivers application headroom.
- Far-field
- 3-mic
- Voice-initiated
Qualcomm Smart Headset Reference Design
The first solution qualified by Amazon for Bluetooth headsets and with support for the Alexa Mobile Accessory (AMA) protocol.
- Close-talk
- 2-mic
- Push-to-Talk
Broadcom BCM972180 Voice STB Solution
A reference solution for set-top-boxes using the Alexa Smart Screen SDK and smart home skills for entertainment devices.
- Far-field
- 2-mic
- Voice-initiated
EveryWord™ AFE Module and Solution by ArkX Laboratories
Streamline the path to market by starting development on a dev kit based on production ready hardware and firmware modules qualified by Amazon AVS. Featuring Cirrus Logic CS48LV41F far-field voice processor for superior performance. Complete Ultra far-field reference design and development platform qualified by Amazon with both 2 and 4 mics.-Integrated 2-4 mic linear and geometric arrays.
- 9 different integrated mic array configurations
- Pre-loaded with “Alexa” trigger and AVS stack-Headless console for configuration, diagnostics and performance monitoring
Number of Mics
How you want your users to interact with your product determines the number of microphones you select. Voice-enabled devices designed for closer, hands-free interaction can use 1 or 2-mic solutions, whereas far-field products with listening ranges from across the room can benefit from a 4 or 7-mic array. Keep in mind that additional mics may take up more physical space and add incremental costs to your product.
Mic Arrangement
Your product’s form factor determines the arrangement of microphones. Square or circular arrays in a horizontal plane are better for 360-degree, omni-directional listening often utilized in tabletop products like the Amazon Echo or Echo Dot. Linear arrays are better suited for uni-directional listening or wall-mounted products such as connected light switches and thermostats with Alexa built-in like the ecobee4.
Audio Algorithms
Voice processing algorithms enable your device to leverage the full capabilities of the mic array. Noise reduction improves speech recognition in noisy environments, beam forming helps locate the direction of speech, and acoustic echo cancellation allows the user to barge in even when your device is playing loud music. These algorithms, combined with wake word engines, allow voice-initiated interactions and send clear, processed audio to the cloud.
