Skip to main content

​
NovaSonicRealtime

Speech-to-speech conversation with Amazon Nova Sonic on AWS Bedrock, using your AWS credentials. Use it when one model should listen, reason and talk in real time. Authenticates with AWS_ACCESS_KEY_ID from your environment, or an explicit api_key.

​
Fields

​
str | None
default:"UNSET"
AWS region hosting Bedrock Nova Sonic, e.g. “us-east-1”. Defaults to None (not set).
​
str
required
Nova Sonic model ID, e.g. “amazon.nova-sonic-v1:0”. Required.
​
Mapping[str, Any] | None
default:"UNSET"
Model settings as a dict, such as voice, temperature, top_p and max_tokens. Defaults to None (not set).