System Settings
Transcription Configuration
Configure Azure OpenAI transcription service for speech-to-text and audio processing features.
Overview
Configure Azure OpenAI transcription to enable speech-to-text capabilities for voice input and audio file processing features.
Azure OpenAI Transcription Setup
Configure your Azure OpenAI transcription service for audio processing and speech recognition.
Required Information:
- Credential Name: Display name for identification (e.g., "Azure OpenAI Transcription")
- API Endpoint: Your Azure OpenAI service endpoint (e.g.,
https://your-resource.openai.azure.com/) - API Key: Your Azure OpenAI API key
- Deployment Name: Name of your transcription model deployment (recommended: "gpt-4o-transcribe")
- API Version: Azure OpenAI API version
Setup Instructions:
- Create an Azure OpenAI resource in your Azure subscription
- Deploy a transcription model (recommended:
gpt-4o-transcribe) - Obtain your API endpoint and API key from the Azure portal
- Configure the transcription credentials in your platform settings
- Save the configuration to enable audio transcription features
Supported Transcription Models:
- gpt-4o-transcribe
- gpt-4o-mini-transcribe
Testing Your Configuration
After setting up transcription credentials, verify the configuration works correctly:
How to Test
- Save Configuration: Complete all required fields and save your transcription credentials
- Check Status: The system will automatically test the connection and show the status
- Test Audio Input: Try using voice input or upload an audio file to verify transcription is working
Troubleshooting
Common Issues:
- Invalid API Key: Ensure your Azure OpenAI API key is correct and has transcription permissions
- Wrong Endpoint: Verify the API endpoint matches your Azure OpenAI resource URL
- Model Deployment: Confirm your transcription model is deployed and the deployment name is correct
- Network Access: Ensure your platform can reach the Azure OpenAI endpoint