Picovoice/rhino
On-device Speech-to-Intent engine powered by deep learning
Extracts structured intent and slot values from natural language commands using deep neural networks trained on real-world speech, enabling contextual understanding beyond simple keyword matching. Provides self-service context customization through Picovoice Console for domain-specific applications, with SDKs spanning embedded systems (ARM Cortex-M, Arduino), mobile (iOS/Android), web browsers, and desktop platforms. Optimized for low-latency on-device inference with minimal computational overhead suitable for IoT and edge deployment.
698 stars. Actively maintained with 18 commits in the last 30 days.
Stars
698
Forks
94
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 14, 2026
Commits (30d)
18
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Picovoice/rhino"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
yandexdataschool/speech_course
YSDA course in Speech Processing.
MycroftAI/adapt
Adapt Intent Parser
IBM/BigLittleNet
Official repository for Big-Little Net
espnet/interspeech2019-tutorial
INTERSPEECH 2019 Tutorial Materials
Picovoice/speech-to-intent-benchmark
benchmark for Speech-to-Intent engines