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.

Real-time voice AI applications v1.0.0

Use this resource to build a low-latency voice AI application

New

  • 585 downloads
  • 151 likes
  • 236 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install realtime-voice-ai-apps-2

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 chooses and assembles voice building blocks: the OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription, ElevenLabs for synthesis and LiveKit for real-time infrastructure. It stresses streaming, interruption handling and the risk of depending on a single provider. You get a fast, scalable voice architecture.

Mostly picked by

Updated November 2, 2026

Card for the “Real-time voice AI applications” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: capabilities, requirements and provider choices
  • sub-skills/: Vapi, Deepgram and ElevenLabs, non-streaming pipeline and pitfalls (interruptions, single-provider lock-in)

Good fit for

  • You want to add a voice to a web or mobile application
  • Your voice assistant responds too slowly

Not for

    Tags

    • voice
    • realtime
    • transcription
    • text to speech

    About

    You say

    “Add a real-time voice conversation to my site, with transcription and a natural voice.”

    Card for the “Real-time voice AI applications” 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 build a low-latency voice AI application
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE2.4 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md1.7 KB
    • sub-skills/deepgram-stt-elevenlabs-tts.md2.1 KB
    • sub-skills/ignoring-interruptions.md0.2 KB
    • sub-skills/non-streaming-pipeline.md0.2 KB
    • sub-skills/openai-realtime-api.md2.1 KB
    • sub-skills/single-provider-lock-in.md0.4 KB
    • sub-skills/vapi-voice-agent.md1.8 KB

    Origin and licence

    Listed unmodified

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

    Notice

    « voice-ai-development » (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.