From f0774268cc83145da2b92786b7646a386c801fe9 Mon Sep 17 00:00:00 2001 From: Paul Kompfner Date: Wed, 19 Mar 2025 21:58:46 -0400 Subject: [PATCH] Rename gpt-4o-transcribe-latest to gpt-4o-transcribe in OpenAIRealtimeBetaLLMService --- CHANGELOG.md | 2 +- src/pipecat/services/openai_realtime_beta/events.py | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 660cf5c82..6825a62f5 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -130,7 +130,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - Added support in `OpenAIRealtimeBetaLLMService` for a slate of new features: - - The `'gpt-4o-transcribe-latest'` input audio transcription model, along + - The `'gpt-4o-transcribe'` input audio transcription model, along with new `language` and `prompt` options specific to that model. - The `input_audio_noise_reduction` session property. diff --git a/src/pipecat/services/openai_realtime_beta/events.py b/src/pipecat/services/openai_realtime_beta/events.py index 88638b5fd..3a18833d2 100644 --- a/src/pipecat/services/openai_realtime_beta/events.py +++ b/src/pipecat/services/openai_realtime_beta/events.py @@ -14,7 +14,7 @@ from pydantic import BaseModel, Field # # session properties # -InputAudioTranscriptionModel = Literal["whisper-1", "gpt-4o-transcribe-latest"] +InputAudioTranscriptionModel = Literal["whisper-1", "gpt-4o-transcribe"] class InputAudioTranscription(BaseModel): @@ -29,9 +29,9 @@ class InputAudioTranscription(BaseModel): prompt: Optional[str] = None, ): super().__init__(model=model, language=language, prompt=prompt) - if self.model != "gpt-4o-transcribe-latest" and (self.language or self.prompt): + if self.model != "gpt-4o-transcribe" and (self.language or self.prompt): raise ValueError( - "Fields 'language' and 'prompt' are only supported when model is 'gpt-4o-transcribe-latest'" + "Fields 'language' and 'prompt' are only supported when model is 'gpt-4o-transcribe'" )