deepgeek/gradio-webrtc
2
0
Fork 0
mirror of https://github.com/HumanAIGC-Engineering/gradio-webrtc.git synced 2026-02-04 17:39:23 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
35a4073064768ec2dd8f53444259d5ea6ee0cb07
gradio-webrtc/cookbook/index.html
github-actions[bot] 35a4073064 Deployed 0264cbd with MkDocs version: 1.6.1
2025-06-17 12:04:47 +00:00

1182 lines
55 KiB
HTML
Raw Blame History

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="canonical" href="https://fastrtc.org/cookbook/">
<link rel="prev" href="../userguide/api/">
<link rel="next" href="../deployment/">
<link rel="icon" href="../fastrtc_logo.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.14">
<title>Cookbook - FastRTC</title>
<link rel="stylesheet" href="../assets/stylesheets/main.342714a4.min.css">
<link rel="stylesheet" href="../assets/stylesheets/palette.06af60db.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<link rel="stylesheet" href="../stylesheets/extra.css">
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/github-dark.min.css">
<script>__md_scope=new URL("..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr" data-md-color-scheme="fastrtc-dark" data-md-color-primary="indigo" data-md-color-accent="indigo">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
</div>
<div data-md-component="announce">
</div>
<header class="md-header md-header--shadow" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href=".." title="FastRTC"
class="md-header__button md-logo" aria-label="FastRTC" data-md-component="logo">
<img src="../fastrtc_logo.png" alt="logo">
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
FastRTC
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Cookbook
</span>
</div>
</div>
</div>
<div style="display: flex; align-items: center; margin-right: 1rem;">
<a href="https://hf.co/fastrtc" target="_blank" rel="noopener noreferrer">
<img src="/hf-logo.svg"
onerror="this.onerror=null; this.src='https://huggingface.co/datasets/freddyaboulton/bucket/resolve/main/hf-logo.svg';"
style="height: 24px; margin-right: 10px;">
</a>
<a href="https://gradio.app" target="_blank" rel="noopener noreferrer">
<img src="/gradio-logo.svg"
onerror="this.onerror=null; this.src='https://huggingface.co/datasets/freddyaboulton/bucket/resolve/main/gradio-logo.svg';"
style="height: 24px; margin-right: 10px;">
</a>
<a href="https://discord.gg/TSWU7HyaYu" target="_blank" rel="noopener noreferrer">
<img src="/Discord-Symbol-White.svg" style="height: 16px; margin-right: 10px;">
</a>
</div>
<div class="md-header__source">
<a href="https://github.com/gradio-app/fastrtc" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.7.2 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81"/></svg>
</div>
<div class="md-source__repository">
fastrtc
</div>
</a>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href=".." title="FastRTC" class="md-nav__button md-logo" aria-label="FastRTC" data-md-component="logo">
<img src="../fastrtc_logo.png" alt="logo">
</a>
FastRTC
</label>
<div class="md-nav__source">
<a href="https://github.com/gradio-app/fastrtc" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.7.2 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81"/></svg>
</div>
<div class="md-source__repository">
fastrtc
</div>
</a>
</div>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href=".." class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2" >
<label class="md-nav__link" for="__nav_2" id="__nav_2_label" tabindex="0">
<span class="md-ellipsis">
User Guide
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2">
<span class="md-nav__icon md-icon"></span>
User Guide
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../userguide/streams/" class="md-nav__link">
<span class="md-ellipsis">
Core Concepts
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../userguide/audio/" class="md-nav__link">
<span class="md-ellipsis">
Audio Streaming
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../userguide/video/" class="md-nav__link">
<span class="md-ellipsis">
Video Streaming
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../userguide/audio-video/" class="md-nav__link">
<span class="md-ellipsis">
Audio-Video Streaming
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../userguide/gradio/" class="md-nav__link">
<span class="md-ellipsis">
Gradio
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../userguide/api/" class="md-nav__link">
<span class="md-ellipsis">
API
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
Cookbook
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../deployment/" class="md-nav__link">
<span class="md-ellipsis">
Deployment
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../advanced-configuration/" class="md-nav__link">
<span class="md-ellipsis">
Advanced Configuration
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_6" >
<label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="0">
<span class="md-ellipsis">
Plugin Ecosystem
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_6">
<span class="md-nav__icon md-icon"></span>
Plugin Ecosystem
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../text_to_speech_gallery/" class="md-nav__link">
<span class="md-ellipsis">
Text-to-Speech Gallery
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../speech_to_text_gallery/" class="md-nav__link">
<span class="md-ellipsis">
Speech-to-Text Gallery
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../turn_taking_gallery/" class="md-nav__link">
<span class="md-ellipsis">
Turn-taking Gallery
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../utils/" class="md-nav__link">
<span class="md-ellipsis">
Utils
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../faq/" class="md-nav__link">
<span class="md-ellipsis">
Frequently Asked Questions
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_9" >
<label class="md-nav__link" for="__nav_9" id="__nav_9_label" tabindex="0">
<span class="md-ellipsis">
API Reference
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_9_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_9">
<span class="md-nav__icon md-icon"></span>
API Reference
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../reference/stream/" class="md-nav__link">
<span class="md-ellipsis">
Stream
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../reference/reply_on_pause/" class="md-nav__link">
<span class="md-ellipsis">
Pause Detection Handlers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../reference/stream_handlers/" class="md-nav__link">
<span class="md-ellipsis">
Stream Handlers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../reference/utils/" class="md-nav__link">
<span class="md-ellipsis">
Utils
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../reference/credentials/" class="md-nav__link">
<span class="md-ellipsis">
TURN Credentials
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1>Cookbook</h1>
<style>
.tag-button {
cursor: pointer;
opacity: 0.5;
transition: opacity 0.2s ease;
}
.tag-button > code {
color: var(--supernova);
}
.tag-button.active {
opacity: 1;
}
</style>
<p>A collection of applications built with FastRTC. Click on the tags below to find the app you're looking for!</p>
<div class="tag-buttons">
<button class="tag-button" data-tag="audio"><code>Audio</code></button>
<button class="tag-button" data-tag="video"><code>Video</code></button>
<button class="tag-button" data-tag="llm"><code>LLM</code></button>
<button class="tag-button" data-tag="text"><code>Text</code></button>
<button class="tag-button" data-tag="computer-vision"><code>Computer Vision</code></button>
<button class="tag-button" data-tag="real-time-api"><code>Real-time API</code></button>
<button class="tag-button" data-tag="voice-chat"><code>Voice Chat</code></button>
<button class="tag-button" data-tag="code-generation"><code>Code Generation</code></button>
<button class="tag-button" data-tag="stopword"><code>Stopword</code></button>
<button class="tag-button" data-tag="transcription"><code>Transcription</code></button>
<button class="tag-button" data-tag="sambanova"><code>SambaNova</code></button>
<button class="tag-button" data-tag="groq"><code>Groq</code></button>
<button class="tag-button" data-tag="elevenlabs"><code>ElevenLabs</code></button>
<button class="tag-button" data-tag="kyutai"><code>Kyutai</code></button>
<button class="tag-button" data-tag="agentic"><code>Agentic</code></button>
<button class="tag-button" data-tag="local"><code>Local Models</code></button>
<button class="tag-button" data-tag="electron"><code>Electron</code></button>
</div>
<script>
function filterCards() {
const activeButtons = document.querySelectorAll('.tag-button.active');
const selectedTags = Array.from(activeButtons).map(button => button.getAttribute('data-tag'));
const cards = document.querySelectorAll('.grid.cards > ul > li > p[data-tags]');
cards.forEach(card => {
const cardTags = card.getAttribute('data-tags').split(',');
const shouldShow = selectedTags.length === 0 || selectedTags.some(tag => cardTags.includes(tag));
card.parentElement.style.display = shouldShow ? 'block' : 'none';
});
}
document.querySelectorAll('.tag-button').forEach(button => {
button.addEventListener('click', () => {
button.classList.toggle('active');
filterCards();
});
});
</script>
<div class="grid cards">
<ul>
<li>
<p data-tags="audio,llm,voice-chat"><img alt="🗣" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f5e3.svg" title=":speaking_head:" /><img alt="🦙" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f999.svg" title=":llama:" /> <strong>Talk to Llama 4</strong></p>
<hr />
<p>Talk to Llama 4 using Groq + Cloudflare.</p>
<p><video width=98% src="https://github.com/user-attachments/assets/f6d09e47-5e40-4296-b6cd-11d7f68baee2" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/fastrtc/talk-to-llama4"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/talk-to-llama4/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,llm,text,voice-chat"><img alt="🗣" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f5e3.svg" title=":speaking_head:" /><img alt="🦙" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f999.svg" title=":llama:" /> <strong>Integrated Textbox</strong></p>
<hr />
<p>Talk or type to any LLM with FastRTC's integrated audio + text textbox.</p>
<p><video width=98% src="https://github.com/user-attachments/assets/35c982a1-4a58-4947-af89-7ff287070ef5" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/fastrtc/integrated-textbox"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/integrated-textbox/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,video,real-time-api"><img alt="🗣" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f5e3.svg" title=":speaking_head:" /><img alt="👀" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f440.svg" title=":eyes:" /> <strong>Gemini Audio Video Chat</strong></p>
<hr />
<p>Stream BOTH your webcam video and audio feeds to Google Gemini. You can also upload images to augment your conversation!</p>
<p><video width=98% src="https://github.com/user-attachments/assets/9636dc97-4fee-46bb-abb8-b92e69c08c71" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/fastrtc/gemini-audio-video"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/gemini-audio-video"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Gradio UI</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/gemini-audio-video/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,real-time-api,voice-chat"><img alt="🗣" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f5e3.svg" title=":speaking_head:" /> <strong>Google Gemini Real Time Voice API</strong></p>
<hr />
<p>Talk to Gemini in real time using Google's voice API.</p>
<p><video width=98% src="https://github.com/user-attachments/assets/ea6d18cb-8589-422b-9bba-56332d9f61de" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/fastrtc/talk-to-gemini"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/talk-to-gemini-gradio"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Gradio UI</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/talk-to-gemini/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,real-time-api,voice-chat"><img alt="🗣" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f5e3.svg" title=":speaking_head:" /> <strong>OpenAI Real Time Voice API</strong></p>
<hr />
<p>Talk to ChatGPT in real time using OpenAI's voice API.</p>
<p><video width=98% src="https://github.com/user-attachments/assets/178bdadc-f17b-461a-8d26-e915c632ff80" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/fastrtc/talk-to-openai"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/talk-to-openai-gradio"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Gradio UI</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/talk-to-openai/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="llm,stopword,sambanova"><img alt="🤖" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f916.svg" title=":robot:" /> <strong>Hello Computer</strong></p>
<hr />
<p>Say computer before asking your question!
<video width=98% src="https://github.com/user-attachments/assets/afb2a3ef-c1ab-4cfb-872d-578f895a10d5" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/fastrtc/hello-computer"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/hello-computer-gradio"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Gradio UI</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/hello-computer/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,llm,code-generation,groq,stopword"><img alt="🤖" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f916.svg" title=":robot:" /> <strong>Llama Code Editor</strong></p>
<hr />
<p>Create and edit HTML pages with just your voice! Powered by Groq!</p>
<p><video width=98% src="https://github.com/user-attachments/assets/98523cf3-dac8-4127-9649-d91a997e3ef5" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/fastrtc/llama-code-editor"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/llama-code-editor/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,llm,voice-chat,agentic"><img alt="🗣" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f5e3.svg" title=":speaking_head:" /> <strong>SmolAgents with Voice</strong></p>
<hr />
<p>Build a voice-based smolagent to find a coworking space!</p>
<p><video width=98% src="https://github.com/user-attachments/assets/ddf39ef7-fa7b-417e-8342-de3b9e311891" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/burtenshaw/coworking_agent/"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/burtenshaw/coworking_agent/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,llm,voice-chat"><img alt="🗣" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f5e3.svg" title=":speaking_head:" /> <strong>Talk to Claude</strong></p>
<hr />
<p>Use the Anthropic and Play.Ht APIs to have an audio conversation with Claude.</p>
<p><video width=98% src="https://github.com/user-attachments/assets/fb6ef07f-3ccd-444a-997b-9bc9bdc035d3" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/burtenshaw/coworking_agent"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/burtenshaw/coworking_agent"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Gradio UI</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/talk-to-claude/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,llm,voice-chat,groq,elevenlabs"><img alt="🎵" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f3b5.svg" title=":musical_note:" /> <strong>LLM Voice Chat</strong></p>
<hr />
<p>Talk to an LLM with ElevenLabs!</p>
<p><video width=98% src="https://github.com/user-attachments/assets/584e898b-91af-4816-bbb0-dd3216eb80b0" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/fastrtc/llm-voice-chat"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/llm-voice-chat-gradio"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Gradio UI</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/llm-voice-chat/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,transcription,groq"><img alt="🎵" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f3b5.svg" title=":musical_note:" /> <strong>Whisper Transcription</strong></p>
<hr />
<p>Have whisper transcribe your speech in real time!</p>
<p><video width=98% src="https://github.com/user-attachments/assets/87603053-acdc-4c8a-810f-f618c49caafb" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/fastrtc/whisper-realtime"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/whisper-realtime-gradio"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Gradio UI</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/whisper-realtime/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="llm,stopword,sambanova"><img alt="🤖" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f916.svg" title=":robot:" /> <strong>Talk to Sambanova</strong></p>
<hr />
<p>Talk to Llama 3.2 with the SambaNova API.
<video width=98% src="https://github.com/user-attachments/assets/92e4a45a-b5e9-45cd-b7f4-9339ceb343e1" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/fastrtc/talk-to-sambanova"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/talk-to-sambanova-gradio"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Gradio UI</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/talk-to-sambanova/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,llm,code-generation,stopword,sambanova"><img alt="🗣" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f5e3.svg" title=":speaking_head:" /> <strong>Hello Llama: Stop Word Detection</strong></p>
<hr />
<p>A code editor built with Llama 3.3 70b that is triggered by the phrase "Hello Llama".
Build a Siri-like coding assistant in 100 lines of code!</p>
<p><video width=98% src="https://github.com/user-attachments/assets/3e10cb15-ff1b-4b17-b141-ff0ad852e613" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/hey-llama-code-editor"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/hey-llama-code-editor/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,llm,voice-chat"><img alt="🗣" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f5e3.svg" title=":speaking_head:" /> <strong>Audio Input/Output with mini-omni2</strong></p>
<hr />
<p>Build a GPT-4o like experience with mini-omni2, an audio-native LLM.</p>
<p><video width=98% src="https://github.com/user-attachments/assets/58c06523-fc38-4f5f-a4ba-a02a28e7fa9e" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/mini-omni2-webrtc"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/mini-omni2-webrtc/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,llm,voice-chat,kyutai"><img alt="🗣" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f5e3.svg" title=":speaking_head:" /> <strong>Kyutai Moshi</strong></p>
<hr />
<p>Kyutai's moshi is a novel speech-to-speech model for modeling human conversations.</p>
<p><video width=98% src="https://github.com/user-attachments/assets/becc7a13-9e89-4a19-9df2-5fb1467a0137" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/talk-to-moshi"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/talk-to-moshi/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,llm,voice-chat"><img alt="🗣" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f5e3.svg" title=":speaking_head:" /> <strong>Talk to Ultravox</strong></p>
<hr />
<p>Talk to Fixie.AI's audio-native Ultravox LLM with the transformers library.</p>
<p><video width=98% src="https://github.com/user-attachments/assets/e6e62482-518c-4021-9047-9da14cd82be1" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/talk-to-ultravox"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/talk-to-ultravox/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,llm,voice-chat"><img alt="🗣" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f5e3.svg" title=":speaking_head:" /> <strong>Talk to Llama 3.2 3b</strong></p>
<hr />
<p>Use the Lepton API to make Llama 3.2 talk back to you!</p>
<p><video width=98% src="https://github.com/user-attachments/assets/3ee37a6b-0892-45f5-b801-73188fdfad9a" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/llama-3.2-3b-voice-webrtc"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/llama-3.2-3b-voice-webrtc/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,llm,voice-chat"><img alt="🤖" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f916.svg" title=":robot:" /> <strong>Talk to Qwen2-Audio</strong></p>
<hr />
<p>Qwen2-Audio is a SOTA audio-to-text LLM developed by Alibaba.</p>
<p><video width=98% src="https://github.com/user-attachments/assets/c821ad86-44cc-4d0c-8dc4-8c02ad1e5dc8" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/talk-to-qwen-webrtc"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/talk-to-qwen-webrtc/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="video,computer-vision"><img alt="📷" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f4f7.svg" title=":camera:" /> <strong>Yolov10 Object Detection</strong></p>
<hr />
<p>Run the Yolov10 model on a user webcam stream in real time!</p>
<p><video width=98% src="https://github.com/user-attachments/assets/f82feb74-a071-4e81-9110-a01989447ceb" controls style="text-align: center"></video></p>
<p><a href="https://huggingface.co/spaces/fastrtc/object-detection"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/fastrtc/object-detection/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="video,computer-vision"><img alt="📷" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f4f7.svg" title=":camera:" /> <strong>Video Object Detection with RT-DETR</strong></p>
<hr />
<p>Upload a video and stream out frames with detected objects (powered by RT-DETR) model.</p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/rt-detr-object-detection-webrtc"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/rt-detr-object-detection-webrtc/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio"><img alt="🔈" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f508.svg" title=":speaker:" /> <strong>Text-to-Speech with Parler</strong></p>
<hr />
<p>Stream out audio generated by Parler TTS!</p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/parler-tts-streaming-webrtc"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://huggingface.co/spaces/freddyaboulton/parler-tts-streaming-webrtc/blob/main/app.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,transcription,local"><img alt="🗣" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f5e3.svg" title=":speaking_head:" /> <strong>Real Time Transcription with On-device Whisper 🤗</strong></p>
<hr />
<p>Transcribe speech in real time using Whisper via the Transformers library, running on your device!</p>
<p><a href="https://github.com/sofi444/realtime-transcription-fastrtc/blob/main/main.py"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,electron"><img alt="🗣" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f5e3.svg" title=":speaking_head:" /> <strong>Talk to Claude - Electron App</strong></p>
<hr />
<p>An Electron desktop application that uses FastRTC to enable voice conversations with Claude.</p>
<p><video width=98% src="https://github.com/user-attachments/assets/df4628e4-ef0f-4a78-ab9b-1ed2374b1cae" controls style="text-align: center"></video></p>
<p><a href="https://github.com/swairshah/voice-agent"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> Demo</a></p>
<p><a href="https://github.com/swairshah/voice-agent"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
<li>
<p data-tags="audio,real-time-api"><img alt="🗣" class="twemoji lg middle" src="https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/1f5e3.svg" title=":speaking_head:" /> <strong>Azure Realtime API</strong></p>
<hr />
<p>Use the Azure Realtime API to create a real-time voice chat with GPT-4o.</p>
<p><a href="https://github.com/freddyaboulton/fastrtc/tree/main/demo/talk_to_azure_openai"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="m11.28 3.22 4.25 4.25a.75.75 0 0 1 0 1.06l-4.25 4.25a.749.749 0 0 1-1.275-.326.75.75 0 0 1 .215-.734L13.94 8l-3.72-3.72a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215m-6.56 0a.75.75 0 0 1 1.042.018.75.75 0 0 1 .018 1.042L2.06 8l3.72 3.72a.749.749 0 0 1-.326 1.275.75.75 0 0 1-.734-.215L.47 8.53a.75.75 0 0 1 0-1.06Z"/></svg></span> Code</a></p>
</li>
</ul>
</div>
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"base": "..", "features": ["content.code.copy", "content.code.annotate", "navigation.indexes"], "search": "../assets/javascripts/workers/search.d50fe291.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
<script src="../assets/javascripts/bundle.13a4f30d.min.js"></script>
<script src="https://cdn.jsdelivr.net/npm/marked/marked.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js"></script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink