Multilingual On-Device Speech-to-Text: Even Better and Stronger

From speech analytics to video subtitles, speech-to-text software brings new ideas to life. Leopard Speech-to-Text has created even more opportunities with cloud-level accuracy on the device, combining the best of the cloud and on-device processing.

Leopard Speech-to-Text, now officially supports seven new languages: French, German, Italian, Japanese, Korean, Portuguese, and Spanish. More developers can build private, reliable, cost-effective transcription software with production-ready, easy-to-use, and cross-platform Leopard Speech-to-Text.

Try It

The web demo below converts voice data to text in eight languages: English, French, German, Italian, Japanese, Korean, Portuguese, and Spanish. The demo runs within your web browser, meaning the audio is processed locally without using 3rd party cloud services. Transcribe an existing audio file or record a new one to see it yourself.

Start Building Now

Building with intuitive and cross-platform Leopard Speech-to-Text SDKs doesn’t require any experience in Machine Learning. Anyone can start transcribing with a few lines of code.

o = pvleopard.create(access_key)

transcript, words = 
  o.process_file(path)
Build with Python

Train Use-case Specific Speech Models

Leopard Speech-to-Text offers cloud-level accuracy out-of-the-box. However, some use cases and industries, such as healthcare, finance, or legal, have special terminology that cannot be accurately predicted by generic speech models.

Custom Vocabulary & Keyword Boosting features allow developers to customize speech-to-text models specific to their application on the no-code Picovoice Console .