Overview Test your voice agents using text instead of phone calls. 10x faster and 90% cheaper - ideal for workflow validation, regression testing, and CI/CD pipelines.
Use voice testing for ASR/TTS validation and final production checks.
Supported Providers ElevenLabs
Retell
Vapi
Custom WebSocket
Code
Configure Chat Provider
Go to Agent Settings → Chatbot Integrations
Select ElevenLabs from provider dropdown
Enter your Assistant ID from ElevenLabs
Save configuration
Run Tests
Go to Evaluator page
Select scenarios
Click “Run as Text” button
View Results
Results appear in the dashboard with conversation transcript, metric evaluations, and function calls.
Create Chat Agent in Retell
Log in to Retell dashboard
Navigate to your voice agent
Click “Copy as chat agent”
Copy the Agent ID of the new chat agent
Configure in Cekura
Go to Agent Settings → Chatbot Integrations
Select Retell from provider dropdown
Enter your Chat Agent ID
Save configuration
Run Tests
Go to Evaluator page
Select scenarios
Click “Run as Text”
Configure Chat Provider
Go to Agent Settings → Chatbot Integrations
Select Vapi from provider dropdown
Enter your Assistant ID from Vapi
Save configuration
Run Tests
Go to Evaluator page
Select scenarios
Click “Run as Text”
Set Up WebSocket Server
Use the example implementation or build your own: git clone https://github.com/vocera-ai/llm-websocket-server-example.git cd llm-websocket-server-example python3 -m venv .venv source .venv/bin/activate pip install -r requirements.txt python main.py
Update your OpenAI API key in main.py before starting the server.
WebSocket Message Format: Your server must handle message types: response (text), function_call, function_result, and end_of_conversation. Example response message: { "type" : "response" , "response" : "Hello! How can I help?" }
See Custom Integration Guide for complete message format details.
Expose Server
For local development, use ngrok: ngrok http 127.0.0.1:8765
Convert the https:// URL to wss:// for WebSocket connection.
Configure in Cekura
Go to Agent Settings → Chatbot Integrations
Select Custom from provider dropdown
Enter your WebSocket URL (starting with wss://)
Save configuration
Run Tests
Go to Evaluator page
Select scenarios
Click “Run as Text”
Run chat tests programmatically via API. For complete API documentation including authentication, request parameters, response format, and code examples in multiple languages, see: Run Evaluator Text API Reference Quick Example curl --request POST \ --url https://api.cekura.ai/test_framework/v1/scenarios/run_scenarios_text/ \ --header 'X-CEKURA-API-KEY: <api-key>' \ --header 'Content-Type: application/json' \ --data '{ "agent_id": 123, "scenarios": [456, 789], "frequency": 1, "name": "Chat Test Run" }'
Troubleshooting
Error: "Chat provider not configured"
Common causes:
Incorrect Assistant/Agent ID
Custom WebSocket server not accessible
Agent disabled or unpublished
Debug steps:
Verify your ID is correct
For Custom: check server is running and URL is accessible
Test provider’s API directly
Check Cekura dashboard for error details
Cannot find "Run as Text" button
Checklist:
✅ Chat provider configured in Agent Settings
✅ On Evaluator page (not Calls/Runs)
✅ At least one scenario selected
Button appears next to “Run Tests” in Evaluator header. Refresh page if not visible. Tips Use chat tests for rapid iteration and CI/CD. Run voice tests on critical scenarios before production deployment.
Tag scenarios as “critical” or “smoke-test” to run targeted test suites in your pipeline.
Next Steps Need help? Contact [email protected] 
