autogen_ext.agents.video_surfer.tools#
- extract_audio(video_path: str, audio_output_path: str) str[source]#
Extracts audio from a video file and saves it as an MP3 file.
- Parameters:
video_path – Path to the video file.
audio_output_path – Path to save the extracted audio file.
- Returns:
Confirmation message with the path to the saved audio file.
- get_screenshot_at(video_path: str, timestamps: List[float]) List[Tuple[float, ndarray[Any, Any]]][source]#
Captures screenshots at the specified timestamps and returns them as Python objects.
- Parameters:
video_path – Path to the video file.
timestamps – List of timestamps in seconds.
- Returns:
List of tuples containing timestamp and the corresponding frame (image). Each frame is a NumPy array (height x width x channels).
- get_video_length(video_path: str) str[source]#
Returns the length of the video in seconds.
- Parameters:
video_path – Path to the video file.
- Returns:
Duration of the video in seconds.
- save_screenshot(video_path: str, timestamp: float, output_path: str) None[source]#
Captures a screenshot at the specified timestamp and saves it to the output path.
- Parameters:
video_path – Path to the video file.
timestamp – Timestamp in seconds.
output_path – Path to save the screenshot. The file format is determined by the extension in the path.
- transcribe_audio_with_timestamps(audio_path: str) str[source]#
Transcribes the audio file with timestamps using the Whisper model.
- Parameters:
audio_path – Path to the audio file.
- Returns:
Transcription with timestamps.
- async transcribe_video_screenshot(video_path: str, timestamp: float, model_client: ChatCompletionClient) str[source]#
Transcribes the content of a video screenshot captured at the specified timestamp using OpenAI API.
- Parameters:
video_path – Path to the video file.
timestamp – Timestamp in seconds.
model_client – ChatCompletionClient instance.
- Returns:
Description of the screenshot content.