Vigorus STT
AI-generatedSummary
Transcribes audio files provided as binary input by sending them to a local Vigorus AI Speech-to-Text endpoint and returns the recognized text along with any additional response data.
Inputs
- binary data (required) — The audio file to be transcribed must be provided as binary data in the input item. The node reads the first binary property available in each input item.
Output shape
A list of JSON objects, one per input audio file, each containing the transcription text under the key 'transcription' plus any other fields returned by the endpoint.
If the transcription endpoint returns a non-JSON response, the node wraps it under the 'transcription' key. Supports error handling per item with optional continue on fail behavior.
Examples
Example 1: Transcribe audio files from an earlier node providing audio binary data
Connect a node that outputs audio files as binary data to this node. It will send each audio file to the Vigorus local STT HTTP service and output the transcription results for each file.