Picovoice is committed to becoming the developer-first voice AI platform for adding voice to anything. The introduction of the Free Tier provided more than 10,000 developers with state-of-the-art voice recognition. The launch of Speech-to-Text engines has made Picovoice the first and only ubiquitous end-to-end edge voice AI platform. Open-source and reproducible benchmarks have brought transparency to the voice tech industry.

Today, Picovoice is pleased to share its unprecedented technology with more developers by introducing voice AI SDKs for Italian, Japanese, Korean and Portuguese. With the existing support for English, German, French and Spanish languages, now developers can train branded wake words and custom voice commands in eight languages.

Hello, Hallo, Bonjour, Ciao, こんにちは, 안녕하세요, Hola, Olá Polyglot Voice Interfaces

Picovoice’s approach to multilingual support is to provide the ability to run multiple speech models simultaneously. Therefore, anyone can create voice experiences that run across platforms and in multi-languages. In the demo below, you can interact with the smart lamp in English, German, French, Italian, Japanese, Korean, Portuguese and Spanish. The demo runs without accessing external services within a web browser. Once the demo is loaded, turn off your internet connection and it will keep working!


Click to activate

  • Hot Pink
  • Lime Green
  • Deep Sky Blue

  • Knallpink
  • Limettengrün
  • Himmelblau

  • Rosado Fuerte
  • Lima Verde
  • Celeste Profundo

  • Rose Vif
  • Vert Citron
  • Bleu Ciel Foncé

  • Rosa Caldo
  • Verde Lime
  • Azzurro

  • 桃色
  • 萌黄
  • 空色

  • 핫 핑크
  • 라임 그린
  • 깊은 하늘색

  • Rosa Choque
  • Verde Limão
  • Azul Celeste

Start Building Now!

Anyone can create an account on Picovoice Console to train branded wake words and custom voice commands without writing a single line of code. Platform-optimized voice AI models can be downloaded instantly and deployed onto the target platform using the Picovoice SDK in minutes.

Get in Touch

Picovoice is built by developers for developers. Although developers can start building immediately without engaging with anyone from the team, your feedback is an essential part of the process. For technical feedback and bugs, please create a GitHub issue. For commercial inquiries, even for the languages we currently do not support, feel free to contact sales with the details of the opportunity and requirements.

Why Picovoice?

Picovoice empowers organizations to build private, responsive and cost-effective voice products with its Porcupine Wake Word, Rhino Speech-to-Intent, Leopard Speech-to-Text, Octopus Speech-to-Index and Cobra Voice Activity Detection engines. Its stack can run anywhere from embedded devices to web browsers, resulting in an immersive experience.