Nova 2.5 Sonic

Amazon’s speech-to-speech model for real-time voice agents on Bedrock.

Nova 2.5 Sonic is Amazon’s speech-to-speech model for natural, real-time voice agents. AWS says it improves reasoning, instruction following and tool-calling accuracy and lowers latency compared with Nova 2 Sonic, without publishing figures. It offers expressive voices in seven languages, controllable turn-taking, mixed voice and text in one session, asynchronous tool calling and a 256K-token context, on Amazon Bedrock in four regions.

Provider
Amazon
Type
Text-to-speech
Released
Oct 5, 2026
Input
audio, text
Output
audio, text
Open weights
No

Best for

Strengths

More from Amazon

Sources