{"slug": "webhook-tool-filler-messages-now-available-for-telnyx-ai-assistants", "title": "Webhook Tool Filler Messages Now Available for Telnyx AI Assistants", "summary": "Telnyx launched filler messages for AI Assistants, allowing developers to script utterances during webhook tool calls to keep callers engaged instead of facing silence. The feature supports deterministic, tiered messages at request start and after configurable delays, improving voice AI call retention.", "body_md": "[Contact us](https://telnyx.com/contact-us)\n\n[Log in](https://portal.telnyx.com)\n\nAI Assistants can now speak scripted utterances at the start of a webhook tool call and during long-running requests. Callers stay engaged while the assistant waits on an external API, database lookup, or third-party model, instead of sitting in silence.\n\nSilence is where voice AI calls die. A webhook tool call that takes 8 to 12 seconds for a database lookup or third-party API leaves the caller staring at dead air, and on a phone call that reads as broken, not loading. Most voice platforms either go silent and lose the caller, or ask the LLM to improvise filler, which rambles, drifts off-brand, and can't be tuned.\n\nThis lets you script the wait-state UX the same way you script the conversation flow. \"Let me look that up for you\" at the start, \"still working on this\" at 5 seconds, \"almost there\" at 15 seconds. Deterministic, tiered, and per-tool. The same control you have over the conversation now extends to the gaps the conversation depends on.\n\nEach filler message has a `type`\n\nof `request_start`\n\n(spoken immediately when the tool call begins) or `request_response_delayed`\n\n(spoken after `timing_ms`\n\nmilliseconds if the response has not yet arrived). The `timing_ms`\n\nfield accepts 100 to 120000 ms and is only required for delayed messages. Once the response arrives, any remaining delayed messages are skipped.\n\n```\n{\n  \"filler_messages\": [\n    { \"type\": \"request_start\", \"content\": \"Let me look that up for you.\" },\n    { \"type\": \"request_response_delayed\", \"content\": \"Still working on this.\", \"timing_ms\": 5000 },\n    { \"type\": \"request_response_delayed\", \"content\": \"Almost there.\", \"timing_ms\": 15000 }\n  ]\n}\n```\n\n**Learn more** in the [AI Assistants docs](https://developers.telnyx.com/docs/inference/ai-assistants) or the [Telnyx docs](https://developers.telnyx.com).", "url": "https://wpnews.pro/news/webhook-tool-filler-messages-now-available-for-telnyx-ai-assistants", "canonical_source": "https://telnyx.com/release-notes/webhook-tool-filler-messages", "published_at": "2026-07-06 00:00:00+00:00", "updated_at": "2026-07-07 01:55:58.945311+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "natural-language-processing"], "entities": ["Telnyx"], "alternates": {"html": "https://wpnews.pro/news/webhook-tool-filler-messages-now-available-for-telnyx-ai-assistants", "markdown": "https://wpnews.pro/news/webhook-tool-filler-messages-now-available-for-telnyx-ai-assistants.md", "text": "https://wpnews.pro/news/webhook-tool-filler-messages-now-available-for-telnyx-ai-assistants.txt", "jsonld": "https://wpnews.pro/news/webhook-tool-filler-messages-now-available-for-telnyx-ai-assistants.jsonld"}}