Picovoice provides speech recognition software that runs entirely on the device rather than in the cloud. Its engines cover wake word detection, speech-to-text, intent parsing, speaker identification and noise suppression, and they ship as SDKs for microcontrollers, mobile phones, browsers and Linux systems. Developers in consumer electronics, automotive, healthcare and industrial applications use the tools to add private voice interfaces without network dependencies or per-request fees.
Focus: on-device voice ai, speech recognition.
Tags: voice · speech recognition · wake word · sdk · privacy
More edge ai companies
Blumind
Analog AI processors for always-on audio and sensor inference in microwatt budgets
Connect Tech
Canadian maker of carrier boards and rugged systems for NVIDIA Jetson modules
AAEON
Embedded boards and BOXER edge AI systems built on Intel, NVIDIA Jetson and Hailo