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.

Pipecat: real-time voice and multimodal bots v1.0.0

Use this resource to build a real-time voice or multimodal bot

New

  • 502 downloads
  • 140 likes
  • 227 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install realtime-voice-bot-pipecat

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 assembles a speech-recognition, language-model and speech-synthesis pipeline, picks the WebRTC or WebSocket transport, sets up context through RTVI and handles function calls. It keeps API keys on the server and prepares deployment.

Mostly picked by

Updated November 2, 2026

Card for the “Pipecat: real-time voice and multimodal bots” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: mental model, recipes and pitfalls
  • references/pipeline-and-frames.md: pipelines and frames
  • references/pipecat-cloud.md: deploying to Pipecat Cloud

Good fit for

  • You build a voice agent for customer support
  • You want to deploy a WebRTC voice bot

Not for

    Tags

    • voice
    • realtime
    • webrtc
    • pipecat
    • agents

    About

    You say

    “Build a Pipecat voice bot that answers questions about my website, over a WebRTC transport.”

    Card for the “Pipecat: real-time voice and multimodal bots” skill

    Skill published by itechmeat 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 real-time voice or multimodal bot
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.4 KB
    • references/cli.md7.4 KB
    • references/client-sdks-rtvi.md3.5 KB
    • references/context-management.md3.1 KB
    • references/core-concepts.md2.2 KB
    • references/deployment.md2.6 KB
    • references/files-and-images.md7.7 KB
    • references/function-calling.md6.2 KB
    • references/installation.md1.6 KB
    • references/llm-inference.md6.3 KB
    • references/migration-1-0.md2.4 KB
    • references/pipecat-cloud.md5.3 KB
    • references/pipeline-and-frames.md5.4 KB
    • references/server-pipeline-apis.md4.8 KB
    • references/server-runner.md4.2 KB
    • references/server-services.md1.2 KB
    • references/session-initialization.md2.7 KB
    • references/speech-input-and-turn-detection.md6.6 KB
    • references/text-to-speech.md7.3 KB
    • references/transports.md5.9 KB
    • references/troubleshooting.md1.2 KB
    • SKILL.md25.1 KB

    Origin and licence

    Listed unmodified

    Author
    itechmeat
    Source
    github.com/itechmeat/llm-code/tree/509c4e00400e83eced7a4313cd34de87698e63c2/skills/pipecat
    Licence
    MIT

    Notice

    « pipecat » (itechmeat, 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.