Skip to main content
Speech-to-text with Navana’s Bodhi API, using your Navana key. Suited to Indian languages and 8 kHz phone-call audio. Authenticates with NAVANA_API_KEY from your environment, or an explicit api_key.

​
Fields

​
str | None
default:"UNSET"
Your Navana customer ID, issued with your API key. Defaults to None (not set).
​
str
default:"UNSET"
Bodhi model name, e.g. “en-general-v2-8khz”. Pick one that matches the language and audio sample rate. Defaults to ‘en-general-v2-8khz’.
​
str
default:"UNSET"
Language code of the speech, e.g. “en” or “hi”. Defaults to ‘en’.
​
int | None
default:"UNSET"
Sample rate of incoming audio in Hz. Leave unset to detect it automatically. Defaults to None (not set).
​
bool
default:"True"
Also send partial transcripts to the client app. Partial results are always used for interruption and turn detection either way. Defaults to True.