[ STACK LIBRARY ]

Picovoice

Visit website

ABOUT

On-device voice AI platform with wake word, speech-to-intent, and streaming transcription engines.

Picovoice builds an end-to-end voice AI platform that processes audio entirely on-device. Its engines include Porcupine for custom wake words, Rhino for speech-to-intent, Cobra for voice activity detection, Cheetah for streaming speech-to-text, and Leopard for batch transcription. Developers customize models in the browser-based Picovoice Console without ML expertise and deploy across microcontrollers, Raspberry Pi, Android, iOS, web, Linux, macOS, and Windows. The company positions on-device processing as private by design, with no cloud dependency at runtime.

STACK COVERAGE

Speech-to-Text

On-device voice AI SDK, Wake word detection, Voice activity detection

DETAILS

HQ COUNTRY

Canada

FOUNDED

2018

LANGUAGES

Multilingual

DEPLOYMENT

On-device/Embedded, SDK

PRICING MODEL

Subscription

COMPANY STAGE

Seed

Is this your company? To claim this listing or update its details, contact us at sunil@uniocommunity.com

UNIOVOICE AI STACK LIBRARY

Trusted by Unio

Picovoice

Speech-to-Text

On-device voice AI platform with wake word, speech-to-intent, and streaming transcription engines.

On-devicevoiceAISDK,Wakeworddetection,Voiceactivitydetection

Layer: Speech-to-Text
Market: Global
HQ: Canada
Founded: 2018
Deployment: On-device/Embedded, SDK
Pricing: Subscription
Languages: Multilingual
Stage: Seed

Picovoice

Picovoice

ABOUT

STACK COVERAGE

DETAILS

Picovoice

More in this layer

SpeechRouter

3Play Media

AI-coustics