Async tools for voice AI to avoid blocking conversations on slow back ends

We just shipped a small architectural update for voice AI assistants that fixes a recurring issue where slow backend calls were blocking live conversations.

In most voice agents today, when the assistant needs to query a database, CRM, or third-party API, the entire conversation pauses until that request finishes. Even a few seconds of silence feels broken on a call.

The approach we shipped separates triggering a backend request from delivering the result.

The assistant can fire a webhook asynchronously and continue the conversation immediately. The backend does its work in the background and, when it’s done (seconds later), pushes the result back into the live call using a call control ID. The assistant receives that context mid-call and incorporates it naturally.

This allows for patterns like continuing a conversation while waiting for slow lookups, running multiple backend requests in parallel, and injecting external context into an active call without restarting it.

This is part of Telnyx’s AI Assistants platform.

Full technical write-up and API details are in the release notes here:https://telnyx.com/release-notes/async-webhook-tools-ai-assi...

Happy to answer questions or hear feedback from anyone building voice or real-time systems.