PicoBlog
Hey Picovoice, let’s add voice AI SDKs for Italian, Japanese, Korean and Portuguese!
July 19, 2022
Picovoice is committed to becoming the developer-first voice AI platform for adding voice to anything....
Differences between voicebots and chatbots
June 19, 2022
With the advances in artificial intelligence (AI), there have been a lot of buzzwords going around: bot, chatbot, virtual assistant, voice a...
Voice Tech to improve productivity by freeing the hands and eyes of workers
June 16, 2022
Workers in agriculture, utility, manufacturing, maintenance & repair, construction or warehouse management and distribution are considered d...
Evaluating audio transcription engines
June 16, 2022
Recent advances in deep learning have made voice technology more accurate, accessible, and affordable. However, now with the availability, c...
Cutting the cloud-dependency of voice AI
June 16, 2022
Picovoice has recently announced its Speech-to-Text engines. Now, developers have access to voice recognition technology for all needs and t...
Smart Vending Machines of the Future with Voice AI
June 15, 2022
Technology adaption in vending machines is highly correlated with revenue growth. COVID-19 differentiated the vending machine operators with...
How to Enable Voice Search for Web and Mobile Applications
June 14, 2022
“Voice Search” is a term used for both voice-enabled search to retrieve information and find phrases in audio files. The first one is also k...
Voice Search: How to Find Spoken Keywords and Phrases in Audio Files
June 14, 2022
I have hundreds, thousands of audio files from meetings (lectures, news, call centre recordings, podcasts). Is there software to search part...
Five Questions with Conversation Design Expert Erika Hall
May 16, 2022
Learn how to apply human-centered design principles from Erika Hall of Mule Design. Tips on conversational AI to improve voice user experien...
10 Questions with Dr Monica Lam, Professor of Computer Science at Stanford University
March 30, 2022
Professor Lam and Picovoice met through a shared passion: enabling private voice interactions and making the voice technology available to a...
Speech-to-Text 2.0: Better, Faster, Stronger
March 8, 2022
Picovoice achieves cloud-level accuracy with tiny Speech-to-Text models, addressing privacy, cost, and reliability problems of the $30 Billi...
Unlocking the voice data
March 6, 2022
IDC predicts that new data generated globally will reach 175 ZB by 2025 compared to 64.2 ZB in 2020. More than 80% of 175 ZB will be...
Post COVID-19 Era: Voice Applications in Stores
February 22, 2022
Some changes we adopt during these uncertain times could be viewed as opportunities to enhance the customer experience and daily life. From ...
HIPAA Compliant Voice Tech in Healthcare
February 15, 2022
Picovoice’s HIPAA-compliant technology streamlines healthcare workflows and improves the patient experience....
New Era for Podcast Publishers
February 8, 2022
Picovoice engines for audio transcription and indexing help publishers uncover the value of unstructured voice data....
Post COVID-19 Era: Empowering Ageing Population with Voice
February 1, 2022
The US, Canada, France, Japan, and Germany are just a few of 34 countries where more than 20% of the population will be over 65 years old by...
5 Tips for Voice User Experience Design
January 25, 2022
Many digital-first enterprises follow human-centered design principles and iterate products when it comes to graphic user interfaces. With P...
Post COVID-19 Era: Back to the office
January 18, 2022
The COVID-19 has changed our lives in many ways. While only 5% of work hours were spent at home at the beginning of 2020, it went up to 60% ...
Building voice products with your favourite SDK
January 11, 2022
Picovoice is built by developers for developers. There’s an exhaustive list of SDKs that are available to build voice products with Picovoic...
Picovoice 2021 Wrapped
December 20, 2021
It’s been a busy year at Picovoice. In case you missed some of our news, we summarized them....
V2.0 Feature Tour
December 14, 2021
We are excited to announce the release of Porcupine and Rhino version 2.0, which achieves major accuracy improvements....
Introducing Picovoice’s Free Tier
December 6, 2021
Anyone with an email address or a GitHub account can use Picovoice to train voice models and deploy them, even commercially, for free....
Not Another Metaverse Post
November 16, 2021
ARVRSpeech RecognitionWake WordVoice CommandsUnityiOSAndroidWebPicovoice's edge-first architecture makes it a perfect choice for low-latency and power-sensitive AR/VR applications....
Voice-Enabled Web
November 9, 2021
WebWake WordVoice CommandsVoice SearchReactAngularVueWebAssemblyPicovoice cross-browser SDK is unique as it offers a hands-free web experience across browsers without risking your users’ trust or inflatin...
Octopus: Picovoice's Voice Search Engine
November 2, 2021
Speech-to-IndexVoice SearchSpeech-to-TextSpeech RecognitionPicovoice Speech-to-Index directly searches audio without relying on text representation....
Cobra: Picovoice’s Voice Activity Detection Engine
October 26, 2021
Voice Activity DetectionVADVoice User InterfacesVUIVoice activity detection (VAD) is a crucial component of many speech processing solutions. VAD detects the presence of a human voice within ...
Picovoice Enables Voice Picking
September 28, 2021
Wake Word DetectionSpeech-to-IntentVoice User InterfacesVUIVoice PickingVoice picking, also known as voice-directed picking, speech-based picking, pick by voice, or pick-to-voice, uses speech recognition and natu...
A Voice AI Browser Extension
July 20, 2021
Wake Word DetectionWebAssemblyWeb Audio APIWebExtension APIGoogle ChromeUsing the Porcupine SDK for Web, we’ve created a proof-of-concept Chrome extension that offers multiple wake word options to trigger a Googl...
Picovoice Web SDKs now Available
April 13, 2021
MicrophoneNLUOffline Voice AIPrivacyWeb Audio APIWeb WorkersWebAssemblyReactAngularVueTypeScriptElectronPicovoice has released its Web SDK with out-of-the-box support across all major frameworks, including Angular, React, and Vue. Picovoice is ...
The First No-Code Voice AI Platform for Microcontrollers
February 22, 2021
Picovoice ShepherdMicrocontrollersArm Cortex-MEnd-to-End Voice PlatformLocal Voice RecognitonOffline Speech RecognitionVoice User InterfacesCustomers can create voice models within their browsers instantly, using Picovoice Console. Once the models are trained, they can be downloa...
Announcing German Language Support and Plans to Go Multilingual
February 8, 2021
MultilingualPolyglotDEFRESEnd-to-End Voice PlatformWake Word DetectionSpeech-to-IntentVoice User InterfacesVUIPicovoice announces early access to its private voice AI SDK for the German language....
From GUI to VUI: Voice-Enabling a Cross-Platform .NET Desktop Application
January 5, 2021
.NET SDK.NET CoreCross-platformPicovoice ConsoleEnd-to-End Voice PlatformWake Word DetectionVoice User InterfacesVUIIn this tutorial, I walk you through building a cross-platform desktop app in .NET using Avalonia, and then, replace all add a voice-user in...
Announcing Public Availability of Picovoice Console
December 21, 2020
Picovoice ConsoleEnd-to-End Voice PlatformWake Word DetectionSpeech-to-IntentVoice User InterfacesVUIPicovoice Console is the platform for designing, training, and testing voice interfaces instantly in your browser. No machine learning skill...
Talking Chess: Adding Offline, Cross-Platform Voice Controls to Chess in .NET Core
December 20, 2020
.NET SDK.NET CorePicovoice ConsoleEnd-to-End Voice PlatformWake Word DetectionSpeech-to-IntentVoice User InterfacesVUII recently decided to use our new .NET SDK to build a voice interface for a game. A lot of people are talking chess right now thanks to Netf...
Picovoice’s Alexa, Google, and Siri wake words are now free!
December 6, 2020
Open Voice PlatformVoice InteroperabilityWake Word DetectionPorcupineAlexaHey GoogleOkay GoogleHey SiriApache 2.0We are making all major voice assistant wake words available for free under the permissive Apache 2.0 license: Alexa, Hey Google, Okay Googl...
Offline Voice AI in a Web Browser
July 8, 2020
MicrophoneNLUOffline Voice AIPrivacyWeb Audio APIWeb WorkersWebAssemblyReactAngularVueTypeScriptCDNOffline Voice AI in a browser might sound a bit contradictory. After all, doesn’t using a web browser mean you’re online? But even if you’re...
Porcupine™ Wake Word Engine - V1.8 Feature Tour
May 31, 2020
Wake Word DetectionKeyword SpottingLocal Voice CommandsOffline Speech RecognitionTransfer LearningZero-Shot LearningWe are excited to announce the release of Porcupine version 1.8, which achieves major accuracy and runtime efficiency improvements....
A Strategy Guide for Voice Applications
February 6, 2020
NLUSpeech-to-IndexSpeech-to-IntentVoice SearchDevelopers face myriad choices when building voice products. Although the end results are similar, different approaches carry significant im...
Voice UI on Mobile: Challenges and Opportunities
October 9, 2019
Open SourceCross-PlatformiOSAndroidSpeechRecognizerSiriKitA survey of popular options for adding voice interfaces to a mobile app, starting with cross-platform technologies and then exploring platfo...
Local Speech-to-Text with Cloud-Level Accuracy
September 16, 2019
CloudOfflinePricingRaspberry PiTranscribeSpeech-to-TextVoice recognition has flourished with the growth of cloud-based speech services. Despite the ubiquity of voice-enabled products, processing ...
End-to-End Intent Inference from Speech
August 28, 2019
Speech-to-TextSpeech-to-IntentExtract intent from speech directly, without the expensive and error-prone Speech-to-Text intermediary....
Benchmarking a Wake Word Detection Engine
August 13, 2019
HotwordWake up wordFalse AlarmPicovoice provides an open-source and open-data benchmark for its Porcupine Wake Word Engine....
The Case for Voice AI on the Edge
July 28, 2019
CostEdge AILatencyPrivacyReliabilityVoice AIWith increasing user privacy concerns and regulations (GDPR, HIPAA, etc.), performing natural language understanding using a cloud-based pro...
Picovoice’s Speech-to-Intent Engine
December 25, 2018
Speech-to-IntentA considerable number of use cases when building voice interfaces involve inferring user’s intent from a spoken command....
Yet Another Wake Word Engine
April 23, 2018
Wake up WordHotwordTrigger WordA wake-word engine is a tiny algorithm that monitors a stream of audio for a special wake-word and activates your voice assistant upon detec...