Web calls not triggering AI model despite correct ...
# support
j
Hi, Appreciate if you could help. - Title: "Web calls not triggering AI model despite correct configuration" - Call ID: 0199e745-1a71-7663-87a1-0a8f0f824f18 - Assistant ID: 32ca5a33-99db-4f8a-9c30-cf69e01f1f9e - Issue: Assistant works perfectly in the dashboard test but web calls produce no audio. OpenAI voice connects but totalCharactersUsed=0. GPT model never invoked. - Configuration: firstMessageMode: "assistant-speaks-first" set on both assistant and assistantOverrides
v
Suggestion: Check that your browser is capturing and sending audio by ensuring microphone permissions are granted and no other application is blocking access. In your web call integration, add a quick check like:
Copy code
js
navigator.mediaDevices.getUserMedia({ audio: true })
  .then(() => console.log("Microphone access granted"))
  .catch(err => console.error("Microphone access denied:", err));
If you see an error, resolve the permission or device issue—this is often the root cause when the AI model is not triggered in web calls, even if the dashboard test works. Source: - [Debugging voice agents](https://docs.vapi.ai/debugging)
c
Hi jp, If you are experiencing issues with web calls not triggering the AI model, here are some steps you can follow to troubleshoot: 1. Verify Configuration: - Double-check that
firstMessageMode
is correctly set to "assistant-speaks-first" both in the assistant settings and
assistantOverrides
. - Ensure the
assistantId
used in web calls matches the one configured for successful dashboard tests. 2. Review Call Logs: - Navigate to
Observe > Call Logs
in your [dashboard](https://dashboard.vapi.ai/) to check call statuses and error messages. - Look for any discrepancies in tool execution results or model invocation errors. 3. Test in Dashboard: - Use the "Talk to Assistant" and "Call" functions on the [dashboard](https://dashboard.vapi.ai/) to isolate network issues. 4. Provider Status: - Check the [OpenAI Status Page](https://status.openai.com/) for ongoing issues that might affect voice model operations. 5. Diagnostics: - If no improvements, refer to [this guide](https://docs.vapi.ai/debugging) for common debugging procedures and ensure your AI service providers aren't reporting issues. By following these steps, you can identify and resolve the issue causing the web calls to not trigger the AI model.
5 Views