Feature Requests

More than 1 end of call report is being sent when i test with both a API server webhook and make.com . For example, in a 21 second call, my API Vapi "Watch End of Call Report" received 83 webhooks. Only the last of these 83 webhooks was the end-of-call-report. the rest were assistant.started, speech-update, etc. This is significantly impacting our ability to use this platform as we have had to disable all voice agents.

More than 1 end of call report is being sent when i test with both a API server webhook and make.com . For example, in a 21 second call, my API Vapi "Watch End of Call Report" received 83 webhooks. Only the last of these 83 webhooks was the end-of-call-report. the rest were assistant.started, speech-update, etc. This is significantly impacting our ability to use this platform as we have had to disable all voice agents.

We manage multiple different organizations as a single-tenancy model for each customer. It would be very helpful to have teh ability to handle what each api key can do for an organization. Example: production api key can't use the delete assistant endpoint to delete all of your assistants in a certain organization.

Sometimes I want to update my test setup based on my assistant's prompt being tweaked. It would be nice to respond to this event dynamically so I don't need to upstand a polling job to check for updated times versus just getting a webhook from Vapi.

Can't set up a custom stt from the assistant dashboard. If I patch my assistant via API and set up with a custom STT, the assistant will use deepgramm STT not my custom one. Vapi does not make any request to my STT server and If I open on the assistand dashboard it will show error, that I did not set any STT server.

Hi Team, Thank you for the guide. I have reviewed the documentation, but the issue persists. As requested, here are the specific details regarding the outbound call failures: Call IDs: 019cd28e-ee73-7dc0-8774-4b33fce4c815 019cd271-dbe2-7580-b7e7-1e0cc8f879d5 019cd241-38ca-7140-abfc-db2dd09afb6d Error Details: Error: call.in -progress.error-providerfault-outbound-sip-403-forbidden Direction: Outbound only Behavior: Every outbound call results in a SIP 403 Forbidden error. This is generated by Vapi's SBC before any SIP INVITE reaches Twilio; there is zero SIP traffic in the Twilio logs, notifications, or Monitor events. Vapi Resources: Credential: 713f5ca1-f791-43bb-8a8b-030d3c75909b BYO Phone: 1f47d073-a346-406e-96d0-b27974c8aaa1 Twilio Trunk: TKe6276e2bb66438f3f3c2d82e554397d4 Configurations Tested (All failed with the same 403 error): IP ACL authentication only (Vapi SBC IPs: 44.229.228.186, 44.238.177.138) Credential List authentication only (digest auth) Combined IP ACL and Credential List Wide-open IP ACL (0.0.0.0/1 + 128.0.0.0/1) No authentication Direct IP gateway instead of trunk URI Exact format from Vapi documentation (no auth plan) New credentials and phone numbers Recent Changes: None. This setup has not worked since the initial configuration. Please let me know if you need any further information to resolve this. Best regards, Evan

Right now when I go on the vapi website and I try to sign up on my phone and I sign in with my google account I cannot get past the first question asking me how I heard about vapi.

I would love the ability to edit a squad's membersOverrides.variableValues on the squad edit page. Right now I have to use the API to update this in the squad, which is not user friendly. This would give me the ability to define an assistant once and reuse it in multiple squads with different purposes, such as creating a customer service agent that can handle calls for different websites.

Hi, could we please have the option to send traces to PostHog's LLM Analytics: https://posthog.com/docs/llm-analytics/start-here