Amazon · AI model
Amazon Nova 2 Sonic
Speech-to-speech model for real-time voice conversations on Amazon Bedrock. Accepts speech and text input, returns speech and text, supports tool use and asynchronous tool calling, and has a 1M-token context window.
Last verified Available 4 sources
Key specs
- Provider
- Amazon
- Family
- Amazon Nova
- API identifier
- amazon.nova-2-sonic-v1:0
- Availability
- Available
- Release date
- 2025-12-02
- License
- Proprietary (AWS Customer Agreement)
- Context window
- 1,000,000 tokens
- Max output
- 65,536 tokens
- API access
- Yes
- Consumer app
- Unknown
Capabilities
Inputs
- Text input Yes Cross-modal input: users can switch between speaking and typing
- Image input No
- Audio input Yes Speech input; the model card lists 'Speech' as supported and generic 'Audio' as not supported
- Video input No
- File input Unknown
Outputs
- Text output Yes
- Image output No
- Audio output Yes Speech output
Features
- Reasoning Unknown
- Tool calling Yes Tool use and asynchronous task completion
- Web search Unknown
"Unknown" means we have not verified this capability yet; it does not mean the model lacks it.
Pricing
Estimate your monthly cost →| Dimension | Tier | Price | Since | Verified | Source |
|---|---|---|---|---|---|
| Input tokens | base | $0.33 per 1M tokens | 2026-10-12 | 2026-10-25 | Amazon Bedrock Pricing US East (N. Virginia), on-demand list price; speech-to-speech model pricing table. Text input tokens. Pricing page note: text token pricing applies to uses such as speech-to-text transcription, tool calls and adding conversation history to the session. |
| Output tokens | base | $2.75 per 1M tokens | 2026-10-12 | 2026-10-25 | Amazon Bedrock Pricing US East (N. Virginia), on-demand list price; speech-to-speech model pricing table. Text output tokens. Pricing page note: text token pricing applies to uses such as speech-to-text transcription, tool calls and adding conversation history to the session. |
| Audio input tokens | base | $3.00 per 1M tokens | 2026-10-12 | 2026-10-25 | Amazon Bedrock Pricing US East (N. Virginia), on-demand list price; speech-to-speech model pricing table. Speech input tokens. |
| Audio output tokens | base | $12.00 per 1M tokens | 2026-10-12 | 2026-10-25 | Amazon Bedrock Pricing US East (N. Virginia), on-demand list price; speech-to-speech model pricing table. Speech output tokens. |
Prices are shown in the currency the provider publishes; we never convert currencies.
Compare Amazon Nova 2 Sonic
Guides
About Amazon Nova 2 Sonic
Nova 2 Sonic is Amazon's speech-to-speech foundation model for real-time voice applications, generally available since December 2, 2025 (model ID amazon.nova-2-sonic-v1:0). It is used through the bidirectional streaming API (InvokeModelWithBidirectionalStream) and is officially supported for English, Spanish, German, French, Italian, Portuguese and Hindi. It accepts speech and text input in the same session, generates speech together with text, and supports tool use. It is available in US East (N. Virginia), US West (Oregon), Europe (Stockholm) and Asia Pacific (Tokyo).
Strengths and weaknesses
Strengths
- Speech and text input in the same session, with speech and text output
- Tool use, including asynchronous tool calling while the conversation continues
- 1M-token context window
- Officially supported in seven languages (English, Spanish, German, French, Italian, Portuguese, Hindi)
Weaknesses
- Only available through the bidirectional streaming API, with an 8-minute connection limit and a default quota of 20 concurrent sessions per account and Region (not adjustable)
- No image or video input; cannot be fine-tuned
- Does not support real-time speech-to-speech translation
Sources
Last verified Page updated 2026-10-27