This page lists all languages supported by Cloud Speech-to-Text. For more information on the class tokens available for each language, see the class tokens page.
The basic ASR speech recognition model supports all of these languages.
Language is specified within a recognition request's
languageCode
parameter. As indicated by the table below, the following features only support
a subset of these languages:
- Automatic punctuation
- Speaker diarization (Beta)
- Speech adaptation boost (Beta)
- Enhanced phone call model
- Enhanced video model
To filter by features, click the desired feature dropdowns and select ✔:
Language tags follow the HTTP/1.1 specification, section 3.10.