Update Together services to use canonical settings pattern

- STT/TTS: Use NOT_GIVEN sentinel, Settings alias, and apply_update()
- TTS: Add output_format and encoding params, use audio context
  management, push_start_frame=True, handle binary + JSON audio
- LLM: Update default model to Llama-4-Maverick
- Update examples to use new settings API

examples/foundational/14c-function-calling-together.py

@@ -72,7 +72,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = TogetherLLMService(
         api_key=os.getenv("TOGETHER_API_KEY"),
         settings=TogetherLLMService.Settings(
-            model="meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
             system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )