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

Merge pull request #4450 from pipecat-ai/mb/gpt-realtime-whisper

Browse Source 
Default OpenAI Realtime transcription to gpt-realtime-whisper
This commit is contained in:
Mark Backman
2026-05-13 09:48:33 -04:00
committed by GitHub
parent 9148e307cc 3e8c5c08f4
commit 5fef239b68
11 changed files with 141 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
changelog/4450.changed.md Normal file
View File

@@ -0,0 +1 @@
- Changed the default OpenAI Realtime input audio transcription model from `gpt-4o-transcribe` to `gpt-realtime-whisper` for both `OpenAIRealtimeSTTService` and `OpenAIRealtimeLLMService`. The new model does not accept the `prompt` parameter; if a prompt is supplied alongside `gpt-realtime-whisper`, it is dropped automatically and a warning is logged. To keep using prompt hints, explicitly pin `model="gpt-4o-transcribe"` (or `"gpt-4o-mini-transcribe"`).