[Amazon Nova Sonic](https://docs.aws.amazon.com/nova/latest/nova2-userguide/using-conversational-speech.html) provides real-time, conversational interactions through bidirectional audio streaming. Amazon Nova Sonic processes and responds to real-time speech as it occurs, enabling natural, human-like conversational experiences. Key capabilities and features include:

-   Adaptive speech response that dynamically adjusts delivery based on the prosody of the input speech.
-   Graceful handling of user interruptions without dropping conversational context.
-   Function calling and agentic workflow support for building complex AI applications.
-   Robustness to background noise for real-world deployment scenarios.
-   Multilingual support with expressive voices and speaking styles. Expressive voices are offered, including both masculine-sounding and feminine sounding, in seven languages: English (US, UK, AU, IN), French, Italian, German, Spanish (US), Portuguese (BR), and Hindi.
-   Recognition of varied speaking styles across all supported languages.

## Installation

Python 3.12+ Required

Nova Sonic requires Python 3.12 or higher due to its experimental AWS SDK dependency.

Nova Sonic is included in the base bidirectional streaming dependencies for Strands Agents.

To install it, run:

```bash
pip install 'strands-agents[bidi]'
```

Or to install all bidirectional streaming providers at once:

```bash
pip install 'strands-agents[bidi-all]'
```

## Usage

After installing `strands-agents[bidi]`, you can import and initialize the Strands Agents’ Nova Sonic provider as follows:

```python
import asyncio

from strands.experimental.bidi import BidiAgent
from strands.experimental.bidi.io import BidiAudioIO, BidiTextIO
from strands.experimental.bidi.models import BidiNovaSonicModel
from strands_tools import stop

from strands_tools import calculator


async def main() -> None:
    model = BidiNovaSonicModel(
        model_id="amazon.nova-2-sonic-v1:0",
        provider_config={
            "audio": {
                "voice": "tiffany",
            },
        },
        client_config={"region": "us-east-1"},  # available in us-east-1, us-west-2, eu-north-1, and ap-northeast-1
    )
    # stop tool allows user to verbally stop agent execution.
    agent = BidiAgent(model=model, tools=[calculator, stop])

    audio_io = BidiAudioIO()
    text_io = BidiTextIO()
    await agent.run(inputs=[audio_io.input()], outputs=[audio_io.output(), text_io.output()])


if __name__ == "__main__":
    asyncio.run(main())
```

## Cross-Modal Input

Nova Sonic accepts text input at any point during an active voice session, without interrupting or waiting on the audio stream. Send a [`BidiTextInputEvent`](/pr-cms-3708/docs/user-guide/concepts/bidirectional-streaming/events/index.md#biditextinputevent) the same way you would outside of a live conversation:

```python
from strands.experimental.bidi.types.events import BidiTextInputEvent

await agent.send(BidiTextInputEvent(text="What's the weather in Seattle?"))
```

Text and audio input can be interleaved freely; sending text does not require pausing the microphone or waiting for the model to finish speaking.

## Credentials

Nova Sonic is available in us-east-1, us-west-2, eu-north-1, and ap-northeast-1.

Nova Sonic requires AWS credentials for access. Under the hook, `BidiNovaSonicModel` uses an experimental [Bedrock client](https://github.com/aws/aws-sdk-python/tree/develop/clients/aws-sdk-bedrock-runtime/src/aws_sdk_bedrock_runtime), which allows for credentials to be configured in the following ways:

**Option 1: Environment Variables**

```bash
export AWS_ACCESS_KEY_ID=your_access_key
export AWS_SECRET_ACCESS_KEY=your_secret_key
export AWS_SESSION_TOKEN=your_session_token  # If using temporary credentials
export AWS_REGION=your_region_name
```

**Option 2: Boto3 Session**

```python
import boto3
from strands.experimental.bidi.models import BidiNovaSonicModel


boto_session = boto3.Session(
    aws_access_key_id="your_access_key",
    aws_secret_access_key="your_secret_key",
    aws_session_token="your_session_token",  # If using temporary credentials
    region_name="your_region_name",
    profile_name="your_profile"  # Optional: Use a specific profile
)
model = BidiNovaSonicModel(client_config={"boto_session": boto_session})
```

For more details on this approach, please refer to the [boto3 session docs](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/core/session.html).

## Configuration

### Client Configs

| Parameter | Description | Default |
| --- | --- | --- |
| `boto_session` | A `boto3.Session` instance under which AWS credentials are configured. | `None` |
| `region` | Region under which credentials are configured. Cannot use if providing `boto_session`. | `us-east-1` |

### Provider Configs

| Parameter | Description | Example | Options |
| --- | --- | --- | --- |
| `audio` | `AudioConfig` instance. | `{"voice": "tiffany", "output_rate": 24000}` | [reference](/pr-cms-3708/docs/api/python/strands.experimental.bidi.types.model#AudioConfig); see [supported voices](https://docs.aws.amazon.com/nova/latest/nova2-userguide/sonic-language-support.html) for valid `voice` values |
| `inference` | Session start `inferenceConfiguration`’s (as snake\_case). | `{"top_p": 0.9, "max_tokens": 2048, "temperature": 0.7}` | [reference](https://docs.aws.amazon.com/nova/latest/nova2-userguide/sonic-input-events.html) |
| `turn_detection` | Turn detection sensitivity. Nova Sonic v2 only; raises `ValueError` on v1. | `{"endpointingSensitivity": "MEDIUM"}` | `HIGH`, `MEDIUM`, `LOW` |

Note

The `audio` config accepts any sample rate supported by the underlying model API. Refer to the [Nova Sonic documentation](https://docs.aws.amazon.com/nova/latest/nova2-userguide/using-conversational-speech.html) for the full list of supported rates.

Conversation History Limits

Nova Sonic caps conversation history passed via `messages` at 50KB per message and 200KB total. Messages exceeding the per-message limit are truncated; if the total exceeds 200KB, the oldest messages are dropped until it fits. This happens silently (only visible via debug-level logs) and only applies to history provided at connection start, not to turns generated during the live conversation.

## Troubleshooting

### Module Not Found

If you encounter the error `ModuleNotFoundError: No module named 'aws_sdk_bedrock_runtime'`, this means the experimental Bedrock runtime dependency hasn’t been properly installed in your environment. To fix this, run `pip install 'strands-agents[bidi]'`.

Python Version Requirement

Nova Sonic requires Python 3.12+ due to the experimental AWS SDK dependency. If you’re using an older Python version, you’ll need to upgrade.

### Hanging

When credentials are misconfigured, the model provider does not throw an exception (a quirk of the underlying experimental Bedrock client). As a result, the provider allows the user to proceed forward with a call to `receive`, which emits no events and thus presents an indefinite hanging behavior.

As a reminder, Nova Sonic is only available in us-east-1, us-west-2, eu-north-1, and ap-northeast-1.

## References

-   [Nova Sonic](https://docs.aws.amazon.com/nova/latest/nova2-userguide/using-conversational-speech.html)
-   [Experimental Bedrock Client](https://github.com/aws/aws-sdk-python/tree/develop/clients/aws-sdk-bedrock-runtime)
-   [Python API Reference](/pr-cms-3708/docs/api/python/strands.experimental.bidi.models.nova_sonic#BidiNovaSonicModel)

## Related pages

- [Guardrails](/pr-cms-3708/docs/user-guide/safety-security/guardrails/index.md) (2 shared tags)
- [Amazon Nova](/pr-cms-3708/docs/user-guide/concepts/model-providers/amazon-nova/index.md) (2 shared tags)
- [Bedrock Knowledge Base Store](/pr-cms-3708/docs/user-guide/concepts/memory/bedrock-knowledge-base/index.md) (2 shared tags)
- [Deploying Strands Agents to Amazon Bedrock AgentCore Runtime](/pr-cms-3708/docs/user-guide/deploy/deploy_to_bedrock_agentcore/index.md) (2 shared tags)
- [Python Deployment to Amazon Bedrock AgentCore Runtime](/pr-cms-3708/docs/user-guide/deploy/deploy_to_bedrock_agentcore/python/index.md) (2 shared tags)
- [TypeScript Deployment to Amazon Bedrock AgentCore Runtime](/pr-cms-3708/docs/user-guide/deploy/deploy_to_bedrock_agentcore/typescript/index.md) (2 shared tags)
- [AgentCore Evaluation Dashboard Configuration](/pr-cms-3708/docs/user-guide/evals-sdk/how-to/agentcore_evaluation_dashboard/index.md) (2 shared tags)
- [BidiAgent](/pr-cms-3708/docs/user-guide/concepts/bidirectional-streaming/agent/index.md) (1 shared tag)
- [Events](/pr-cms-3708/docs/user-guide/concepts/bidirectional-streaming/events/index.md) (1 shared tag)
- [Gemini Live](/pr-cms-3708/docs/user-guide/concepts/bidirectional-streaming/models/gemini_live/index.md) (1 shared tag)


## Implementation

### Python

- [harness-sdk/strands-py/src/strands/experimental/bidi/models/nova_sonic.py](https://github.com/strands-agents/harness-sdk/blob/main/strands-py/src/strands/experimental/bidi/models/nova_sonic.py)