Hi VAPI team, I'm building an inbound voice receptionist (Kings Fade Barbers) and have a consistent issue where the assistant goes completely silent after a tool call returns successfully. It only continues speaking once the user says something, then it responds normally. Setup: - Model: GPT-4o Mini (also tested GPT-4.1 and GPT-5.2 Instant — same issue on all, so not model-specific) - Transcriber: Deepgram Nova-3 - Voice: ElevenLabs Flash v2.5 - Custom tool hitting an n8n webhook (check_availability_kings_fade) - Tool returns successfully in 2-3 seconds What happens: 1. User gives a time to book 2. Request Start message fires correctly: 'Let me just check that for you, one moment' 3. Tool executes and returns a result successfully (confirmed in n8n execution logs) 4. Assistant goes silent — does nothing 5. User speaks 6. Assistant then responds with the tool result normally What I've already tried: - Smart Endpointing: tested both Vapi and Livekit — same issue - Silence Timeout: set to 50 seconds - Back off seconds: set to 0 - Wait seconds: set to 0.1 - Server timeout: set to 10 seconds - Temperature: set to 0 - Tested every available model — issue persists across all of them The tool response format from n8n is: { results: [ { toolCallId: 'xxx', result: 'That slot is available.' } Is there a specific turn detection setting, tool call handling configuration, or known issue with the assistant not taking its turn after a tool result is received? Any help would be greatly appreciated.

sounds like a turn-taking issue. try adjusting the silence timeout lower or check if the tool completion signal is properly triggering the next turn.

Hi, thank you for sharing the details. Could you please provide the Call ID for this issue? This will help us investigate further.

019eb31c-2156-7000-a52b-81294641dd5c

sure, we will check and get back to you

thanks!

weird. might be an issue with the tool completion signal not triggering the response. double-check if the webhook is sending a clear end signal. also, maybe try increasing the verbosity level in the logs to catch any missed signals.

Thanks! While you investigate, I wanted to confirm — the webhook is returning this format: json{ "results": [ { "toolCallId": "xxx", "result": "Your booking is confirmed." } ] } Is that the correct format for the tool completion signal? And is there anything specific about how the response should be structured to properly trigger the next turn? Also happy to provide any additional call IDs if needed.

format looks ok. for verbosity, check your logging config in the VAPI settings, might be under 'advanced' or 'debug'. also, ensure your tool completion signal is actually reaching the assistant, not just ending at the webhook.

Hi, I checked the call and noticed that your tools are configured with

"blocking": true

on the

request-start

message, while the corresponding

request-complete

messages do not contain any content. Because of this, once the tool completes, the assistant has no message to speak and remains silent until the caller says something. To resolve this, you can either add content to the

request-complete

messages or remove the blocking behavior from the

request-start

messages (set false)

okay ill check everything, thanks!

Thankyou for choosing Vapi. Have a great day!