OpenAI Audio Transcribe Documentation
Overview
The OpenAI Audio Transcribe node is part of the OpenAI integration in the Vantage workflow engine. Transcribe audio files to text using OpenAI Whisper.
This node uses the OpenAI API through Vantage's managed credential system — no manual token handling required.
Settings
Audio File URL
- Input Type: String
Model
- Input Type: String
- Default Value:
"whisper-1"
Language
- Input Type: String (ISO-639-1)
How It Works
- Receives input data from upstream nodes through configured input ports.
- Authenticates with OpenAI using your connected credentials.
- Executes the API operation with the provided configuration and input data.
- Returns the result through the output port for downstream processing.
Error handling is built in — if the API call fails, the node throws a descriptive error with the failure reason.
Input and Output
- Input: Accepts data in object or array format from upstream nodes.
- Output: Returns the OpenAI API response as structured data.
Use Cases
Workflow Automation
Integrate OpenAI operations into multi-step workflows combining data from multiple sources, transformations, and conditional logic.
Scheduled Operations
Pair with the Schedule Trigger node to run OpenAI operations on a recurring basis.
Event-Driven Pipelines
Combine with other trigger nodes to react to events and automatically execute OpenAI actions.