: Enhance responses by linking the model to a knowledge base through asynchronous tool calls.
Amazon Nova Sonic is a next-generation speech-to-speech model designed for human-like voice conversations with extremely low latency.
: Supports real-time speech-to-speech interaction, expressive voices (11 styles), and natural dialogue handling like pauses and interruptions. Implementation :
Este sitio web utiliza cookies para mejorar la experiencia del usuario y asegurarse de que está funcionando con eficacia.