wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #4152 from vpalmisano/vpalmisano-patch-1

Browse Source 
Fix audio transcript check in base_llm.py
This commit is contained in:
Filipi da Silva Fuchter
2026-03-27 08:34:15 -04:00
committed by GitHub
parent eee47deb34 537d57449e
commit e1bfa4cf21
2 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
changelog/4152.fixed.md Normal file
View File

@@ -0,0 +1 @@
- Fixed a crash in OpenAI LLM processing when the provider returns `chunk.choices[0].delta.audio = None`, which caused `'NoneType' object has no attribute 'get'` errors during audio transcript handling.

6
src/pipecat/services/openai/base_llm.py
View File

@@ -545,8 +545,10 @@ class BaseOpenAILLMService(LLMService):
# When gpt-4o-audio / gpt-4o-mini-audio is used for llm or stt+llm # When gpt-4o-audio / gpt-4o-mini-audio is used for llm or stt+llm
# we need to get LLMTextFrame for the transcript # we need to get LLMTextFrame for the transcript
elif hasattr(chunk.choices[0].delta, "audio") and chunk.choices[0].delta.audio.get( elif (
"transcript" hasattr(chunk.choices[0].delta, "audio")
and chunk.choices[0].delta.audio
and chunk.choices[0].delta.audio.get("transcript")
): ):
await self.push_frame(LLMTextFrame(chunk.choices[0].delta.audio["transcript"])) await self.push_frame(LLMTextFrame(chunk.choices[0].delta.audio["transcript"]))