This page lists all languages supported by Cloud Speech-to-Text. Language is
specified within a recognition request's
parameter. For more information on the
available for each language, see the
class tokens page.
The table below lists the models available for each language. Cloud Speech-to-Text offers multiple recognition models, each tuned to different audio types. The default and command and search recognition models support all available languages. The command and search model is optimized for short audio clips, such as voice commands or voice searches. The default model can be used to transcribe any audio type.
Some languages are supported by additional models, optimized for additional audio types: phone call, enhanced phone call, and enhanced video. These models can recognize speech captured from these audio sources more accurately than the default model. See the enhanced models page for more information.
Some language models are supported by one or more additional features:
To filter by features, click the desired feature dropdowns and select ✔. The table shows only those rows containing a ✔ for the selected feature; the dropdown shows as ✔ and hides the name of the feature:
Language tags follow the HTTP/1.1 specification, section 3.10.