----------------------------- **While I generate an answer, here are some sources that might be helpful**: * [Orchestration Models]() * [Create Assistant]() * [Update Assistant]() * [List Assistants]() -----------------------------

### Answer It sounds like you're experiencing issues with overlapping responses and multiple activations of tool calls within a single conversation session. This could be related to the interruption handling and the management of concurrent API calls in your voice assistant's configuration. To address this, consider reviewing the settings related to interruptions and concurrency in your assistant's configuration. Vapi offers detailed control over managing interruptions, such as through the

numWordsToInterruptAssistant

setting, which specifies how many words to wait for before interrupting the assistant. Additionally, ensure that the response delay (

responseDelaySeconds

) and request delay (

llmRequestDelaySeconds

) settings are configured to prevent the assistant from responding too quickly or frequently, which might be causing overlapping responses [(1)]() . Another aspect to check is the integration with third-party services, such as Slack or other tools being called by the assistant. Ensure that these integrations are managed uniquely per session to prevent multiple instances from being triggered by concurrent requests. If these adjustments do not resolve the issue, it may be helpful to review the specific logs and request headers when the issue occurs to identify any patterns or misconfigurations leading to these overlaps. For further details on managing interruptions and concurrency, you might find the sections related to endpointing and interruption handling in the Vapi documentation helpful.