Amazon Web Services · 2025– · speech-to-speech
Amazon Nova Sonic
Nova Sonic is a speech-to-speech model in the Nova family, not a drop-in Polly voice. It is meant for conversational agents. Sample unavailable on this bench.
Known for
AWS’s answer to GPT Realtime and Gemini Live.
Sample unavailable. No redistributable clip was on file. Listen on the official site rather than a fake waveform.
- Approach
- Spoken dialogue
- Year / era
- 2025
- License class
- commercial
- Cloning
- No
- Streaming
- Yes
- Emotion controls
- Yes
- Languages (tags)
- en
- Official
- Source