diff --git a/CHANGELOG.md b/CHANGELOG.md index fe531bf7f..660cf5c82 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -130,7 +130,8 @@ 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. + - The `'gpt-4o-transcribe-latest'` input audio transcription model, along + with new `language` and `prompt` options specific to that model. - The `input_audio_noise_reduction` session property. ```python @@ -171,9 +172,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - Updated the default model for `CartesiaTTSService` and `CartesiaHttpTTSService` to `sonic-2`. -- Updated the default model for `OpenAIRealtimeBetaLLMService` to - `gpt-4o-realtime-preview-latest`. - - Function calls are now executed in tasks. This means that the pipeline will not be blocked while the function call is being executed. diff --git a/src/pipecat/services/openai_realtime_beta/openai.py b/src/pipecat/services/openai_realtime_beta/openai.py index 4b993c28a..ab78a4451 100644 --- a/src/pipecat/services/openai_realtime_beta/openai.py +++ b/src/pipecat/services/openai_realtime_beta/openai.py @@ -89,8 +89,7 @@ class OpenAIRealtimeBetaLLMService(LLMService): self, *, api_key: str, - # model: str = "gpt-4o-realtime-preview-2024-12-17", - model: str = "gpt-4o-realtime-preview-latest", + model: str = "gpt-4o-realtime-preview-2024-12-17", base_url: str = "wss://api.openai.com/v1/realtime", session_properties: events.SessionProperties = events.SessionProperties(), start_audio_paused: bool = False,