2023 was another busy year at Picovoice with new products, languages, SDKs, team members, and customers. See the 2023 highlights from Picovoice:

New Voice AI Products:

Picovoice added three brand-new products to its portfolio in 2023.

Koala Noise Suppression

In April 2023, Picovoice launched Koala Noise Suppression.

Koala Noise Suppression allows developers to offer elevated experiences by removing background noise from audio in real time while preserving human speech. Powered by deep learning, Koala Noise Suppression enables developers to enhance the quality of conversations on any platform.

Eagle Speaker Recognition

In May 2023, Picovoice announced Eagle Speaker Recognition.

Developers can improve productivity, save costs, and enhance user experience by identifying speakers using their unique voice characteristics with Eagle Speaker Recognition. Eagle, powered by deep learning, enables developers to determine “who is speaking” on any platform with no language or passphrase limitations.

Falcon Speaker Diarization

In December 2023, Picovoice released Falcon Speaker Diarization.

Falcon Speaker Diarization makes transcripts readable and analyzable by differentiating speakers in conversations. Falcon, powered by deep learning, allows developers to identify speakers in an audio stream by finding speaker change points and grouping them.

Try Picovoice’s modular AI models in your browser and deploy them all or choose what works best for you. Picovoice processes voice data locally without sending it to remote servers, offering private and “real” real-time experiences.

17 Languages

Picovoice added nine more languages in 2023, reaching 17 languages in total: English, Arabic, Dutch, Farsi, French, German, Hindi, Italian, Japanese, Korean, Mandarin, Polish, Portuguese, Russian, Spanish, Swedish, and Vietnamese.

If you require a language not listed here, book a session with Picovoice Consulting to get a custom model trained for you!

New Voice AI SDKs

Picovoice released new and improved versions of all engines. The last update was in December 2023. Upgrade to the latest SDKs if you haven’t.

  1. How to record audio from a web browser
  2. Wake word detection with Python
  3. Speech-to-text using NodeJS
  1. Voice Search
  2. Improving speech-to-text accuracy
  3. Local speech-to-text with cloud-level accuracy

Once again, Python was the developers’ first choice this year. If you haven’t yet already, start building with a few lines of Python: