Aparavi DTCInstall

Summary

Transcribe audio content from a file path or binary data to text using the Aparavi DTC platform's audio transcription pipeline.

Inputs

• Input Type (required) — Select the source type of the audio input: File Path for local filesystem audio file, Binary Data from a previous node, or Text Data (not applicable for this operation). Defaults to File Path.
• File Path (required) — Full path to the audio file to transcribe. Required when Input Type is 'file'.
• Binary Property (required) — Name of the binary property containing the audio file to process. Required when Input Type is 'binary'. Defaults to 'data'.
• Options — Optional settings including 'Custom Base URL' to override the default API endpoint, 'Timeout (seconds)' for operation timeout duration, and 'Retry Attempts' for number of retry attempts on failure.

Output shape

a JSON object containing the transcription result with parsed text under keys such as 'text', 'result', 'data', or 'documents'.

The transcription result is returned from the Aparavi backend pipeline response. If processing is still underway, a status token and progress information may be returned. Errors during transcription are surfaced as node execution errors unless 'Continue On Fail' is enabled.

Examples

Example 1: Transcribe an audio file from local path

Set Input Type to 'File Path', provide the full file path to an audio file (e.g., .wav, .mp3), and optionally adjust timeout and retry options.

Example 2: Transcribe audio binary data from previous node

Set Input Type to 'Binary Data', specify the binary property name containing audio data (default is 'data'), then execute to receive transcription text.