Skip to main content

Getting Started with Voice Feature

Prerequisites​

Before using the Voice Feature system, ensure you have:

  • Access to the voice processing interface
  • Appropriate permissions for file uploads
  • LangFlow integration configured
  • At least one automation rule set up

Uploading Your First Audio File​

Step 1: Access the Voice Table​

Navigate to the Voice Feature section and locate the Voice Table interface.

Step 2: Upload Audio File​

  1. Click the upload button or drag and drop your audio file
  2. Supported formats: [List supported audio formats]
  3. Maximum file size: [Specify limit]
  4. The file will immediately appear with "Uploading" status

Step 3: Monitor Processing​

Watch the status progression:

  • Uploading → File transfer in progress
  • Transcribing → Audio-to-text conversion
  • Running Flow → Automation rule processing
  • Completed → All processing finished

Step 4: View Results​

  1. Click the ℹ️ (More Info) button next to your file
  2. Review the complete transcription
  3. Examine Flow processing results
  4. Access any generated metadata

Setting Up Basic Automation​

Quick Rule Creation​

  1. Navigate to the Automation Table
  2. Click "Create New Rule"
  3. Configure:
    • Name: Descriptive rule name
    • Type: Media type (e.g., "audio", "video")
    • Origin: Source identifier
    • Flow: Target LangFlow workflow
    • Status: Enable the rule

Testing Your Setup​

  1. Upload a test audio file matching your rule criteria
  2. Verify automatic processing occurs
  3. Check results in Voice Table
  4. Adjust rules as needed

Next Steps​