Update plugin readme

README.md

@@ -106,7 +106,7 @@ Get a free API key from [Stream](https://getstream.io/). Developers receive **33
 
 | **Plugin Name** | **Description** | **Docs Link** |
 |-------------|-------------|-----------|
-| AWS Polly | TTS plugin using Amazon's cloud-based service with natural-sounding voices and neural engine support | [AWS Polly](https://visionagents.ai/integrations/aws-polly) |
+| AWS | AWS (Bedrock) integration with support for standard LLM (Qwen, Claude with vision), realtime with Nova 2 Sonic, and TTS with AWS Polly | [AWS](https://visionagents.ai/integrations/aws) |
 | Cartesia | TTS plugin for realistic voice synthesis in real-time voice applications | [Cartesia](https://visionagents.ai/integrations/cartesia) |
 | Decart | Real-time video restyling capabilities using generative AI models | [Decart](https://visionagents.ai/integrations/decart) |
 | Deepgram | STT plugin for fast, accurate real-time transcription with speaker diarization | [Deepgram](https://visionagents.ai/integrations/deepgram) |
@@ -225,7 +225,7 @@ While building the integrations, here are the limitations we've noticed (Dec 202
 * Longer videos can cause the AI to lose context. For instance if it's watching a soccer match it will get confused after 30 seconds
 * Most applications require a combination of small specialized models like Yolo/Roboflow/Moondream, API calls to get more context and larger models like gemini/openAI
 * Image size & FPS need to stay relatively low due to performance constraints
-* Video doesn’t trigger responses in realtime models. You always need to send audio/text to trigger a response. 
+* Video doesn’t trigger responses in realtime models. You always need to send audio/text to trigger a response.
 
 ## Star History
 

plugins/aws/README.md

@@ -1,43 +1,101 @@
 # AWS Plugin for Vision Agents
 
-AWS (Bedrock) LLM integration for Vision Agents framework with support for both standard and realtime interactions.
+AWS (Bedrock) integration for Vision Agents framework with support for standard LLM, realtime with Nova Sonic, and text-to-speech with automatic session resumption.
 
 ## Installation
 
 ```bash
-pip install vision-agents-plugins-aws
+uv add vision-agents[aws]
 ```
 
 ## Usage
 
 ### Standard LLM Usage
 
-This example shows how to use qwen3 on bedrock for the LLM.
+The AWS plugin supports various Bedrock models including Qwen, Claude, and others. Claude models also support vision/image inputs.
 
 ```python
+from vision_agents.core import Agent, User
+from vision_agents.plugins import aws, getstream, cartesia, deepgram, smart_turn
+
 agent = Agent(
     edge=getstream.Edge(),
     agent_user=User(name="Friendly AI"),
     instructions="Be nice to the user",
-    llm=aws.LLM(model="qwen.qwen3-32b-v1:0"),
+    llm=aws.LLM(
+        model="qwen.qwen3-32b-v1:0",
+        region_name="us-east-1"
+    ),
     tts=cartesia.TTS(),
     stt=deepgram.STT(),
     turn_detection=smart_turn.TurnDetection(buffer_duration=2.0, confidence_threshold=0.5),
 )
 ```
 
-The full example is available in example/aws_qwen_example.py
+For vision-capable models like Claude:
+
+```python
+llm = aws.LLM(
+    model="anthropic.claude-3-haiku-20240307-v1:0",
+    region_name="us-east-1"
+)
+
+# Send image with text
+response = await llm.converse(
+    messages=[{
+        "role": "user",
+        "content": [
+            {"image": {"format": "png", "source": {"bytes": image_bytes}}},
+            {"text": "What do you see in this image?"}
+        ]
+    }]
+)
+```
 
 ### Realtime Audio Usage
 
-Nova Sonic audio realtime STS is also supported:
+AWS Nova 2 Sonic provides realtime speech-to-speech capabilities with automatic reconnection logic. The default model is `amazon.nova-2-sonic-v1:0`.
+
+```python
+from vision_agents.core import Agent, User
+from vision_agents.plugins import aws, getstream
 
-```python    
 agent = Agent(
     edge=getstream.Edge(),
     agent_user=User(name="Story Teller AI"),
     instructions="Tell a story suitable for a 7 year old about a dragon and a princess",
-    llm=aws.Realtime(),
+    llm=aws.Realtime(
+        model="amazon.nova-2-sonic-v1:0",
+        region_name="us-east-1",
+        voice_id="matthew"  # See available voices in AWS Nova documentation
+    ),
+)
+```
+
+The Realtime implementation includes automatic reconnection logic that reconnects after periods of silence or when approaching connection time limits.
+
+See `example/aws_realtime_nova_example.py` for a complete example.
+
+### Text-to-Speech (TTS)
+
+AWS Polly TTS is available for converting text to speech:
+
+```python
+from vision_agents.plugins import aws
+
+tts = aws.TTS(
+    region_name="us-east-1",
+    voice_id="Joanna",  # AWS Polly voice ID
+    engine="neural",  # 'standard' or 'neural'
+    text_type="text",  # 'text' or 'ssml'
+    language_code="en-US"
+)
+
+# Use in agent
+agent = Agent(
+    llm=aws.LLM(model="qwen.qwen3-32b-v1:0"),
+    tts=tts,
+    # ... other components
 )
 ```
 
@@ -70,14 +128,15 @@ def get_weather(city: str) -> dict:
 
 ### Realtime (aws.Realtime)
 
-The Realtime implementation **fully supports** function calling with AWS Nova Sonic. Register functions using the `@llm.register_function` decorator:
+The Realtime implementation **fully supports** function calling with AWS Nova 2 Sonic. Register functions using the `@llm.register_function` decorator:
 
 ```python
 from vision_agents.plugins import aws
 
 llm = aws.Realtime(
-    model="amazon.nova-sonic-v1:0",
-    region_name="us-east-1"
+    model="amazon.nova-2-sonic-v1:0",
+    region_name="us-east-1",
+    voice_id="matthew"
 )
 
 @llm.register_function(
@@ -97,19 +156,23 @@ def get_weather(city: str) -> dict:
 
 See `example/aws_realtime_function_calling_example.py` for a complete example.
 
-## Running the examples
+## Configuration
 
-Create a `.env` file, or cp .env.example to .env and fill in
+### Environment Variables
+
+Create a `.env` file with the following variables:
 
 ```
 STREAM_API_KEY=your_stream_api_key_here
 STREAM_API_SECRET=your_stream_api_secret_here
 
-AWS_BEARER_TOKEN_BEDROCK=
+AWS_BEDROCK_API_KEY=
 AWS_ACCESS_KEY_ID=
 AWS_SECRET_ACCESS_KEY=
+AWS_REGION=us-east-1
 
-FAL_KEY=
 CARTESIA_API_KEY=
 DEEPGRAM_API_KEY=
-```
+```
+
+Make sure your `.env` file is configured before running the examples.