Introduction

Picovoice is the developer-first platform for building voice products on your terms. Unlike Amazon or Google, Picovoice performs voice recognition entirely on-device while being more accurate. Picovoice is

Accurate — Resilient to noise and reverberation. Picovoice outperforms cloud-based alternatives.
Private & Secure — Voice recognition is entirely offline. Intrinsically private; HIPAA and GDPR compliant.
Zero Latency — Edge-first architecture eliminates unpredictable network delay.
Cross-Platform — Design once, deploy anywhere. Build using familiar languages and frameworks.
Free Tier — Start building for free. No credit card is required.
Self-Service — Design, train, and test voice interfaces instantly in your browser, using Picovoice Console.

Flow

Design

Picovoice Console is a web-based platform for training custom speech models, all within your web browser. No machine learning skills are required. Describe what you need with text and export trained models.

Develop

Exported models from Picovoice Console can run on Picovoice SDKs. Picovoice SDKs run on many platforms and supports most frameworks. The Picovoice Console and SDKs enable you to design, build and iterate fast.

Deploy

Start for free taking advantage of Picovoice Free Tier, even commercially. Deploy without having to maintain complex cloud infrastructure. Avoid hefty cloud fees, limitations, and control imposed by big tech.

Features

Speech-to-Text & Transcription

Picovoice Leopard is the only on-device speech-to-text engine that matches cloud-level accuracy and is under 20 MB. You can use Picovoice Console to train models that understand the custom vocabulary that matters to your use case.

Voice Search & Speech Indexing

Picovoice Octopus Speech-to-Index directly searches speech data without relying on a text representation. It significantly outperforms cloud-based speech-to-text engines on search tasks by removing the out-of-vocabulary and competing hypothesis problems.

Custom Wake Words & Keyword Spotting

Picovoice Porcupine wake word engine detects utterances of given wake phrases. You can train custom wake words using Picovoice Console and then run the exported wake word models on the Picovoice SDK.

Voice Commands & Intent Inference

Picovoice Rhino Speech-to-Intent engine directly infers user's intent from spoken commands within a given domain of interest (context). You can design and train custom contexts for your product using Picovoice Console.

Voice Activity Detection (VAD)

Picovoice Cobra VAD engine detects the presence of speech in a stream of audio in real-time.