Aparavi DTCInstall

Summary

Generate a concise summary of spoken content from an audio input by transcribing the audio and then producing a text summary.

Inputs

• Input Type (required) — Select the format of the input audio data: either a local file path, binary data from a previous node, or text data (text input is not supported for this operation).
• File Path — Full file path to the audio file to process. Required if Input Type is 'File Path'. Not supported in n8n cloud; binary data input should be used instead.
• Binary Property — The name of the binary property containing the audio file; required if Input Type is 'Binary Data'. Defaults to 'data'.
• Options — Optional settings including a custom API base URL, timeout duration in seconds (default 300), and number of retry attempts on failure (default 3).

Output shape

a single JSON object containing the transcription text and a summary text in fields returned as 'documents'; delivered as an output JSON per input item.

The operation reads the audio data, sends it to Aparavi's audio transcription and summarization pipeline, and waits for processing completion. Errors are thrown if file access fails or input type is unsupported. The output JSON includes keys with the original transcription and the generated summary text.