Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Voice agent architecture v1.0.0

Use this resource to design a low-latency voice agent

New

  • 334 downloads
  • 111 likes
  • 199 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install low-latency-voice-agent-design

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent compares speech-to-speech architecture, which is more natural, with a speech-to-text, LLM and text-to-speech pipeline, which is easier to debug. It reasons about the latency budget and about interruptions and end-of-turn detection. You get a reasoned voice architecture and the points to watch.

Mostly picked by

Updated November 2, 2026

Card for the “Voice agent architecture” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: role, capabilities and architecture choices
  • sub-skills/: speech-to-speech architecture, pipeline, voice activity detection and latency budget

Good fit for

  • You want a voice or phone assistant that answers quickly
  • You are choosing between a realtime API and a modular pipeline

Not for

    Tags

    • voice agent
    • latency
    • realtime
    • text to speech

    About

    You say

    “Design an appointment-booking voice agent that answers in under 800 ms.”

    Card for the “Voice agent architecture” skill

    Skill published by dokhacgiakhoa under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to design a low-latency voice agent
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE2.4 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md1.8 KB
    • sub-skills/ignoring-latency-budget.md0 KB
    • sub-skills/long-responses.md0.6 KB
    • sub-skills/pipeline-architecture.md0.1 KB
    • sub-skills/silence-only-turn-detection.md0 KB
    • sub-skills/speech-to-speech-architecture.md0.1 KB
    • sub-skills/voice-activity-detection-pattern.md0.1 KB

    Origin and licence

    Listed unmodified

    Author
    dokhacgiakhoa
    Source
    github.com/dokhacgiakhoa/agent-skills-4-vibe-coding-cli/tree/c4a059bbf7a8d6b2162071f0fbfe74053faa6d20/.agent/skills/voice-agents
    Licence
    MIT

    Notice

    « voice-agents » (dokhacgiakhoa, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.