Get Audio Emotion Insights

Model representing audio metadata and analysis results.

Attributes: created_at (Optional[Any]): Timestamp when the audio was created. status (str): Current processing status of the audio. id (str): Unique identifier for the audio. model_id (str): Models used to process audio. url (str): Storage URL of the audio file. audio_duration (float): Duration of the audio in seconds. task_completion_status (Optional[int]): Status code indicating task completion. user_id (str): ID of the user who uploaded the audio. title (Optional[str]): Optional title for the audio. average_audio_emotions (Optional[dict]): Average emotion scores for the audio. segment_audio_emotions (Optional[list[dict]]): Emotions per audio segment. segment_text_emotions (Optional[list[dict]]): Text-based emotions per segment. summary (Optional[Union[str, Dict[str, Any]]]): Text summary of the audio (string or dict with title, status, summary_body). speakers (Optional[list[dict]]): Detected speaker information. audio_type (str): Declared recording type. Always a string; generic when absent. llm_audio_policy (str): Backend-stamped audio-LLM policy. Always a string; off when absent.