Rhino Speech-to-Intent Engine

Context-aware naturally-spoken command understanding

Arrow (pointing at microphone button)
Press the microphone button to activate the demo
SmallMediumLarge
Single ShotDouble ShotTriple Shot
AmericanoCappuccinoCoffeeEspressoLatteMocha
Private

Private

Everything is processed on-device. Intrinsically HIPAA and GDPR compliant.

Efficient

Efficient

Built upon proprietary deep learning technology. The natural fit for IoT and resource-constrained applications.

Zero Latency Icon

Zero Latency

Edge-first architecture eliminates unpredictable network delay.


Focused speech contexts boost accuracy and efficiency

“Tell me a joke”

Elevator

“Stop at P-2”

“Go to 5”

“Sing a song”

“Recite Shakespeare”

Coffee Maker

“Double shot cappuccino”

“Brew a dark roast coffee”

“What's my horoscope”

“What is the meaning of life”

Smart Lighting

“Dim living room”

“Turn on the porch lights”


Design and iterate with Picovoice Console

Add voice with a few lines of code

# Create an instance of Rhino
handle = pvrhino.create(context_path='/absolute/path/to/context', sensitivity=0.25)
# Process audio
while True:
is_finalized = handle.process(get_next_audio_frame())
if is_finalized:
inference = handle.get_inference()
if inference.is_understood:
intent = inference.intent
slots = inference.slots
# insert inference callback here

Need always-listening voice commands?

Porcupine

Make voice products with Rhino

Start Building