Use LiveKit Inference for the realtime example

README.md

@@ -13,7 +13,7 @@ The starter includes:
   - The default LLM is Gemma 4 31B, an open-weight model [hosted by LiveKit](https://docs.livekit.io/agents/models/llm/livekit/) and tuned for voice AI.
   - The default TTS is [Fish Audio S2.1 Pro](https://docs.livekit.io/agents/models/tts/fishaudio/), an expressive and cost-effective voice.
   - More than 50 other models are available from OpenAI, Cartesia, Deepgram, and other providers.
-  - [Realtime models](https://docs.livekit.io/agents/models/realtime/) and many others are available through the [plugin ecosystem](https://docs.livekit.io/agents/models/#plugins).
+  - [Realtime models](https://docs.livekit.io/agents/models/realtime/) such as OpenAI GPT-Live. Many other models are available through the [plugin ecosystem](https://docs.livekit.io/agents/models/#plugins).
 - [Expressive mode](https://docs.livekit.io/agents/models/tts/expressive/), on by default, so your agent's voice carries emotion and pacing that fit the conversation.
 - [Keyterms](https://docs.livekit.io/agents/models/stt/keyterms/), on by default, so speech recognition gets your names, brands, and jargon right, including names it picks up during the conversation, like a caller's.
 - [LiveKit Turn Detector](https://docs.livekit.io/agents/logic/turns/turn-detector/), which knows when the user has finished speaking, in 14 languages.

src/agent.py

@@ -30,11 +30,8 @@ def __init__(self) -> None:
             # with a realtime model and remove the STT/TTS from the AgentSession
             # (Note: This is for OpenAI GPT-Live, the recommended speech-to-speech
             # model. For other providers, see https://docs.livekit.io/agents/models/realtime/)
-            # 1. Install livekit-agents[openai]
-            # 2. Set OPENAI_API_KEY in .env.local
-            # 3. Add `from livekit.plugins import openai` to the top of this file
-            # 4. Replace the llm argument with:
-            #    llm=openai.realtime.GPTLiveModel(voice="marin"),
+            # Replace the llm argument with the model's LiveKit Inference ID:
+            #    llm="openai/gpt-live-1",
             instructions=textwrap.dedent(
                 """\
                 You are a friendly, reliable voice assistant that answers questions, explains topics, and completes tasks with available tools.