Cheetah Speech-to-Text

Cheetah is an on-device streaming speech-to-text engine. Cheetah is:

Private; All voice processing runs locally.
Accurate
Compact and Computationally-Efficient [2]
Cross-Platform:
- Linux (x86_64)
- macOS (x86_64, arm64)
- Windows (x86_64, arm64)
- Android
- iOS
- Web
- Raspberry Pi (3, 4, 5)

EnglishEnglish

FrenchFrançais

GermanDeutsch

ItalianItaliano

PortuguesePortuguês

SpanishEspañol

Japanese日本語

Korean한국어

Get Started

Anyone who is using Picovoice needs to have a valid AccessKey. AccessKey is your authentication and authorization token for using Picovoice. It also verifies that your usage is within the limits of your account. You must keep your AccessKey secret!

Retrieve AccessKey

Download SDK

Picovoice SDKs are available both on GitHub and via SDK-specific package managers. Follow one of the quick starts to transcribe using Cheetah with your newly-created AccessKey.

Languages

Cheetah Streaming Speech-to-Text currently supports English, French, German, Italian, Portuguese, and Spanish. Default language models can be downloaded from the Cheetah Streaming Speech-to-Text GitHub repository. For other languages, Enterprise Plan customers can reach out to their Picovoice contacts.

Customizations

Picovoice Console allows you to add custom vocabulary (e.g. medical jargon, name of players in a soccer team, etc.) to your Speech-to-Text model. Additionally, it enables you to boost the probability of certain keywords. The latter is useful if you know certain words will be frequent in your use case (e.g. a sales call).

Navigate to Leopard & Cheetah Console from the Picovoice Console landing page.

Create a Model

Create a new model by giving it a name, selecting a language, and clicking on the Create Model button.

Add Custom Vocabulary

Add custom vocabulary by adding them in text form. Optionally, you can enter the pronunciation in IPA format.

Boost Keywords

Boost the probability of frequent words and phrases.

Test

You can test your custom speech-to-text model directly in the browser.

Microphone

Click on the microphone, wait for it to start, and then utter a test sentence. Click on the microphone again to stop and check the result in the text box below.