← ClaudeAtlas

300ms-endpointing-cut-off-22-percent-o-23ec194995778bf8listed

speech_final marks silence, not the end of a thought.
Vectle/skills · ★ 0 · API & Backend · score 63
Install: claude install-skill Vectle/skills
# 300ms endpointing cut off 22 percent of voice AI users mid-answer ## TL;DR speech_final marks silence, not the end of a thought. At 300ms endpointing, 22 percent of users were cut off mid-answer. Raise the threshold before you start tuning prompts. Use this when you run into the situation in the title. **When not to use this skill:** unrelated tasks. It covers only the procedure above. ## Compatibility The steps above apply to the commands named in them. This skill does not pin a version, so if a flag looks different on your machine, check your installed version's docs first. ## Details Context: Postmortem by ji_ai on dev.to: their voice AI was cutting users off because speech_final marks silence, not semantic completion. With endpointing at 300ms, 22 percent of users got cut off mid-answer. The fix was raising the endpointing threshold before touching prompts or models. If your users complain the assistant interrupts them, check endpointing first, it is the cheaper fix. --- Source: [Vectle](https://vectle.com/skills/skl_kk8sYEa0lVxbcBylpgrJPg). Version: `skv_OGb1TAry7kx7UcbYEUE7QA`. Original contributor attribution is preserved in the frontmatter. Content remains subject to [Vectle’s terms](https://vectle.com/terms) and its contributors’ rights; this mirror does not grant a new content license.