Skip to main content

Models and languages

Speechly offers models of different sizes and capabilities for various languages.

Available models

Below you'll find the available models and their specifications. The off-the-shelf speech recognition models are good for basic speech-to-text usage. To improve the model accuracy even further, they should be adapted to your specific domain.

NameSizeCloudOn-deviceOn-premise
large-highaccuray~ 140 MB
small-lowlatency~ 70 MB

Supported languages

Below you'll find the currently supported and planned languages. For enterprise customers we have the capability to add new languages with a few months lead time.

LanguageStatusCloudOn-deviceOn-premise
EnglishFully supported
FinnishPartially supported
SpanishPlanned for 2023
GermanPlanned for 2023
PortuguesePlanned for 2023
FrenchPlanned for 2023
ChineseUnder consideration
JapaneseUnder consideration
KoreanUnder consideration
ArabicUnder consideration

avaialble   planned