Skip to main content

Voice Recording Tool

The Voice Recording step captures voice audio inside a workflow and makes the recording available to later steps. Use it to collect spoken input and then pass the audio into transcription, analysis, or storage steps.

Steps to Use the Voice Recording Tool​

Step 1: Access the Tool​

  • Click on Add User Step.
  • From the available options, select the Voice Recording Tool.

Step 2: Provide the Audio Source​

  • Supply the voice input the step should record. You can pass the source dynamically using the {{variable_name}} syntax — for example {{audio_input}} — to reference a value provided earlier in the workflow.

Step 3: Configure Guardrails Validators (Optional)​

You can set up guardrails validators to ensure the captured recording meets your criteria before it is used downstream.

Step 4: Run the Step​

  1. Run the tool: Click the Run button to capture the recording.
  2. Results: The step returns the recording reference, ready to use in later steps.

Step 5: Use the Results​

Pass the recording into downstream steps — for example Audio to Text to transcribe it, or the Tool Output node to return it.

Tips for Effective Use​

  • Chain with transcription: Feed the recording into Audio to Text when you need a text transcript.
  • Keep payloads lean: Persist only what downstream steps actually need (see Tool Output).
  • Validate input: Use guardrails to catch empty or invalid recordings early.

If you have any questions or need further assistance, please contact the helpdesk ([email protected]).