Usage guide
Setup, environment variables, and Python/JavaScript/Go usage examples.
AzureSTT
Speech-to-text with Azure AI Speech. Good for broad language coverage, phrase-list boosting and telephony audio. Authenticates with AZURE_SPEECH_KEY from your environment, or an explicitapi_key.
Fields
Optional[str]
default:"UNSET"
Azure region of your Speech resource, e.g. “eastus”. Falls back to the AZURE_SPEECH_REGION environment variable. Defaults to None (not set).
str
default:"UNSET"
BCP-47 language code to transcribe, e.g. “en-US” or “fr-FR”. Defaults to ‘en-US’.
Optional[int]
default:"UNSET"
Sample rate of incoming audio in Hz; Azure accepts 8000 or 16000. Leave unset to detect it automatically. Defaults to None (not set).
bool
default:"UNSET"
Turn on phrase-list boosting using the phrases in phrase_list. Defaults to False.
Optional[List[str]]
default:"UNSET"
Names, terms or phrases to recognize more reliably, e.g. product names. Used when enable_phrase_list is on. Defaults to None (not set).
bool
default:"True"
Send partial transcripts to the client as well as final ones. Turn detection and interruptions work either way. Defaults to True.