a few updates

examples/foundational/07e-interruptible-together.py

@@ -55,21 +55,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = TogetherSTTService(api_key=os.getenv("TOGETHER_API_KEY"))
 
-    tts = TogetherTTSService(
+    tts = TogetherTTSService(api_key=os.getenv("TOGETHER_API_KEY"))
+
+    llm = TogetherLLMService(
         api_key=os.getenv("TOGETHER_API_KEY"),
-        voice="tara",
+        settings=TogetherLLMService.Settings(
+            model="Qwen/Qwen3.5-9B",
+            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+        ),
     )
 
-    llm = TogetherLLMService(api_key=os.getenv("TOGETHER_API_KEY"))
-
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
+    context = LLMContext()
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
@@ -100,7 +96,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message({"role": "user", "content": "Please introduce yourself"})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

src/pipecat/services/together/llm.py

@@ -36,7 +36,7 @@ class TogetherLLMService(OpenAILLMService):
         self,
         *,
         api_key: str,
-        base_url: str = "https://api.together.xyz/v1",
+        base_url: str = "https://api.together.ai/v1",
         model: Optional[str] = None,
         settings: Optional[Settings] = None,
         **kwargs,
@@ -45,8 +45,8 @@ class TogetherLLMService(OpenAILLMService):
 
         Args:
             api_key: The API key for accessing Together.ai's API.
-            base_url: The base URL for Together.ai API. Defaults to "https://api.together.xyz/v1".
-            model: The model identifier to use. Defaults to "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo".
+            base_url: The base URL for Together.ai API. Defaults to "https://api.together.ai/v1".
+            model: The model identifier to use.
 
                 .. deprecated:: 0.0.105
                     Use ``settings=TogetherLLMService.Settings(model=...)`` instead.
@@ -56,7 +56,7 @@ class TogetherLLMService(OpenAILLMService):
             **kwargs: Additional keyword arguments passed to OpenAILLMService.
         """
         # 1. Initialize default_settings with hardcoded defaults
-        default_settings = self.Settings(model="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo")
+        default_settings = self.Settings(model=model)
 
         # 2. Apply direct init arg overrides (deprecated)
         if model is not None:

src/pipecat/services/together/stt.py

@@ -296,7 +296,7 @@ class TogetherSTTService(WebsocketSTTService):
         Args:
             evt: The delta event from the server.
         """
-        delta = evt.get("transcript", "")
+        delta = evt.get("delta", "")
         if delta.strip():
             await self.push_frame(
                 InterimTranscriptionFrame(
@@ -321,6 +321,7 @@ class TogetherSTTService(WebsocketSTTService):
                     self._user_id,
                     time_now_iso8601(),
                     result=evt,
+                    finalized=True,
                 )
             )
             await self._handle_transcription_trace(transcript, True, self._settings.language)

src/pipecat/services/together/tts.py

@@ -225,20 +225,17 @@ class TogetherTTSService(WebsocketTTSService):
         Args:
             message: The message dict to serialize and send.
         """
-        try:
-            if not self._disconnecting and self._websocket:
-                await self._websocket.send(json.dumps(message))
-        except Exception as e:
-            if self._disconnecting or not self._websocket:
-                return
-            await self.push_error(
-                error_msg=f"Error sending message: {e}",
-                exception=e,
-            )
+        if not self._disconnecting:
+            await self.send_with_retry(json.dumps(message), self._report_error)
 
-    async def flush_audio(self):
-        """Flush any pending audio and finalize the current context."""
-        logger.trace(f"{self}: flushing audio")
+    async def flush_audio(self, context_id: Optional[str] = None):
+        """Flush any pending audio and finalize the current context.
+
+        Args:
+            context_id: Pipecat TTS context (unused for Together; required for
+                compatibility with :meth:`TTSService.on_turn_context_completed`).
+        """
+        logger.trace(f"{self}: flushing audio (context_id={context_id})")
         await self._ws_send({"type": "input_text_buffer.commit"})
 
     # ------------------------------------------------------------------
@@ -252,7 +249,9 @@ class TogetherTTSService(WebsocketTTSService):
         this method with automatic reconnection on connection errors.
         """
         async for message in self._websocket:
-            if not isinstance(message, str):
+            if isinstance(message, bytes):
+                message = message.decode("utf-8")
+            elif not isinstance(message, str):
                 continue
 
             try: