The basic ASR speech recognition model supports all of these languages.
Language is specified within a recognition request's
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.