diff --git a/CHANGELOG.md b/CHANGELOG.md
index bf6fec1b2..319dce632 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -11,7 +11,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - Added support for the AWS Nova Sonic speech-to-speech model with the new
   `AWSNovaSonicLLMService`.
-  (see https://docs.aws.amazon.com/nova/latest/userguide/speech.html)
+  See https://docs.aws.amazon.com/nova/latest/userguide/speech.html.
+  Note that it requires Python >= 3.12 and `pip install pipecat-ai[aws-nova-sonic]`.
 
 - Added new AWS services `AWSBedrockLLMService` and `AWSTranscribeSTTService`.
 
diff --git a/pyproject.toml b/pyproject.toml
index 7ce167d77..06d7fb0a4 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -41,7 +41,8 @@ Website = "https://pipecat.ai"
 [project.optional-dependencies]
 anthropic = [ "anthropic~=0.49.0" ]
 assemblyai = [ "assemblyai~=0.37.0" ]
-aws = [ "boto3~=1.37.16", "websockets~=13.1", "aws_sdk_bedrock_runtime~=0.0.2" ]
+aws = [ "boto3~=1.37.16", "websockets~=13.1" ]
+aws-nova-sonic = [ "aws_sdk_bedrock_runtime~=0.0.2" ]
 azure = [ "azure-cognitiveservices-speech~=1.42.0"]
 cartesia = [ "cartesia~=1.4.0", "websockets~=13.1" ]
 cerebras = []
diff --git a/src/pipecat/services/aws_nova_sonic/aws.py b/src/pipecat/services/aws_nova_sonic/aws.py
index eab12272c..b53578f5a 100644
--- a/src/pipecat/services/aws_nova_sonic/aws.py
+++ b/src/pipecat/services/aws_nova_sonic/aws.py
@@ -74,7 +74,9 @@ try:
     from smithy_core.aio.eventstream import DuplexEventStream
 except ModuleNotFoundError as e:
     logger.error(f"Exception: {e}")
-    logger.error("In order to use AWS services, you need to `pip install pipecat-ai[aws]`.")
+    logger.error(
+        "In order to use AWS services, you need to `pip install pipecat-ai[aws-nova-sonic]`."
+    )
     raise Exception(f"Missing module: {e}")