Merge pull request #3435 from pipecat-ai/aleix/fix-llm-context-create-audio-message

LLMContext: fix create_audio_message

changelog/3435.fixed.md

@@ -0,0 +1 @@
+- Fixed `LLMContext.create_audio_message()` by correcting an internal helper that was incorrectly declared async while being run in `asyncio.to_thread()`.

src/pipecat/processors/aggregators/llm_context.py

@@ -206,7 +206,7 @@ class LLMContext:
         """
         content = [{"type": "text", "text": text}]
 
-        async def encode_audio():
+        def encode_audio():
             sample_rate = audio_frames[0].sample_rate
             num_channels = audio_frames[0].num_channels