Amazon Nova Sonic
A speech-to-speech foundation model for conversational AI
What is Amazon Nova Sonic?
Amazon Nova Sonic delivers real-time, human-like voice conversations with leading price performance and low latency. Available in Amazon Bedrock via the bidirectional streaming API, the model understands streaming speech in various speaking styles and generates expressive speech responses that dynamically adapt to the prosody of input speech.
Amazon Nova Sonic supports expressive voices, including both masculine-sounding and feminine-sounding voices, in English, Spanish, French, Italian, and German. The model can be utilized across a wide range of applications, including customer support call automation, outbound marketing, voice-enabled personal assistants and agents, and interactive education and language learning.
Key capabilities
Learn more about Amazon Nova Sonic capabilities
Fluid dialog handling and natural turn taking
Handles user interruptions and detects non-verbal cues (e.g., laughter, grunts, inter-sentential pauses, and hesitations) to enable human-like turn-taking in dialogues.
Adaptive speech responses
Nova Sonic’s unified architecture enables it to adapt speech responses to the user’s tone and sentiment.
Low latency
Bidirectional streaming speech I/O with low user perceived latency.
Best-in-class speech recognition
Accurately recognizes streaming speech across accents with robustness to background noise.
Available in multiple languages
Amazon Nova Sonic supports English (including American and British accents), Spanish, French, Italian, and German.
See Amazon Nova Sonic
Amazon Nova Sonic
Model comparison tables
Discover real-world use cases
At ASAPP, we are focused on using generative AI to deliver reliable, secure, and high-performing solutions for improving customer service in contact centers. We’ve been particularly impressed by Amazon Nova Sonic’s highly accurate speech understanding capabilities which allow for more natural voice interactions and precise dialog handling over telephony. We’re excited to continue using Nova Sonic to deliver secure, high-quality, and precise conversations.
Nirmal Mukhi
Nirmal Mukhi, VP AI Engineering at ASAPP
Our goal is to empower the world’s top sports broadcasters, media, federations and teams with magic in the detail of our vast live and historical Opta sports dataset. We’ve been testing Amazon Nova Sonic and have been particularly impressed by the system's low latency, which enables near- instantaneous responses even to complex queries of our model. The intuitive prompting capability and ease of setup have exceeded our expectations, making implementation simple. Overall, Nova Sonic has proven to be a fantastic solution.
Mike Perez
Mike Perez, Chief Operating Officer at Stats Perform
Amazon Nova Sonic enables EF students to practice new vocabulary and refine their pronunciation in a dynamic learning environment. The model is capable of accurately understanding non-native English speakers with a variety of accents. We were also impressed with the barge-in feature of Nova Sonic, where the model quickly reacts to interruptions. The scalability and reliability of the technology will allow us to expand our capacity to serve a larger student population.
Tim Hesse
Tim Hesse, VP AI & Data at Education FirstLearn More with Amazon Nova Sonic Blogs
Getting started with Amazon Nova Sonic
This video provides a step-by-step tutorial on how to use Amazon Nova Sonic in Amazon Bedrock to build your own voice-enabled bot.
Did you find what you were looking for today?
Let us know so we can improve the quality of the content on our pages