🏢 Enterprise AI Consulting
Get dedicated help specific to your use case and for your hardware and software choices.
Consult an AI Expert

It’s been a busy year at Picovoice. In case you missed some of our news, we summarized them. See the highlights of advances in state-of-the-art on-device voice recognition technology. Let us know what you want to see in 2022.

Multilingual Voice Recognition with German Language Support

February 2021 — Picovoice announced early access to its private voice AI SDK for the German language and intentions to invest in French and Spanish voice AI SDKs to enable more voice applications with its state-of-the-art on-device voice recognition technology.

🏢 Enterprise AI Consulting
Get dedicated help specific to your use case and for your hardware and software choices.
Consult an AI Expert

No-Code Voice AI for Microcontrollers

February 2021 — Picovoice announced the public availability of Picovoice Shepherd: the first no-code platform for building voice interfaces on microcontrollers.

Local voice-recognition for the Web

April 2021 — Picovoice released Web SDKs with out-of-the-box support across all major frameworks, including Angular, React, and Vue, bringing local voice recognition to the web.

Multilingual Voice Recognition with Spanish & French Language Support

September 2021 — Picovoice announced public availability to its private voice AI SDK for the Spanish and French languages.

Looking for additional languages? Contact Picovoice Consulting to get custom voice AI models trained for you.

Cobra Voice Activity Detection (VAD)

October 2021 — Picovoice announced the public availability of its VAD engine and open-source benchmark for voice activity detection engines.

Voice Search with Octopus Speech-to-Index

November 2021 — Picovoice announced the public availability of its Speech-to-Index engine, Octopus. Octopus takes a unique approach and makes voice data searchable and discoverable without relying on a text representation.

V2.0 Releases of Porcupine Wake Word & Rhino Speech-to-Intent

December 2021 — V2.0 releases of Porcupine Wake Word and Rhino Speech-to-Intent engines now achieve much higher accuracies than the predecessors.

Making state-of-the-art voice technology now available with the Free Tier

December 2021 — Anyone with an email address, LinkedIn, Google or a GitHub account can train voice models and deploy them, even commercially, for free.

2022

We’ll take a short break and be back in January with more exciting news. More importantly, we want your feedback!