clean up (#199)

Author: Nash0x7E2

examples/01_simple_agent_example/README.md

@@ -12,7 +12,7 @@ This example shows you how to build a basic video AI agent using [Vision Agents]
 - Python 3.13 or higher
 - API keys for:
   - [OpenAI](https://openai.com) (for the LLM)
-  - [Cartesia](https://cartesia.ai/) (for text-to-speech)
+  - [Elevenlabs](https://elevenlabs.io/) (for text-to-speech)
   - [Deepgram](https://deepgram.com/) (for speech-to-text)
   - [Stream](https://getstream.io/) (for video/audio infrastructure)
   - [Smart Turn](https://fal.ai/models/fal-ai/smart-turn) (for turn detection)
@@ -27,11 +27,10 @@ This example shows you how to build a basic video AI agent using [Vision Agents]
 2. Create a `.env` file with your API keys:
    ```
    OPENAI_API_KEY=your_openai_key
-   CARTESIA_API_KEY=your_cartesia_key
+   ELEVENLABS_API_KEY=your_11labs_key
    DEEPGRAM_API_KEY=your_deepgram_key
    STREAM_API_KEY=your_stream_key
    STREAM_API_SECRET=your_stream_secret
-   FAL_KEY=your_fal_key
    ```
 
 ## Running the Example
@@ -59,7 +58,7 @@ agent = Agent(
     agent_user=User(name="My happy AI friend", id="agent"),
     instructions="You're a video AI assistant...",
     llm=openai.LLM(model="gpt-4o-mini"),
-    tts=cartesia.TTS(),
+    tts=elevenlabs.TTS(),
     stt=deepgram.STT(),
     turn_detection=smart_turn.TurnDetection(),
 )
@@ -133,7 +132,7 @@ Edit the `instructions` parameter to change how your agent behaves. The instruct
 You can swap out any component:
 - Try `openai.Realtime()` for lower latency
 - Use `gemini.Realtime()` for Google's model
-- Switch TTS providers to `cartesia.TTS()` or `kokoro.TTS()`
+- Switch TTS providers to `elevenlabs.TTS()` or `kokoro.TTS()`
 
 ### Add Processors