index.htmlā¢24.8 kB
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>VoiceMode MCP - Voice Mode for Claude Code</title>
<meta name="description" content="VoiceMode MCP enables natural voice conversations with Claude Code and other AI coding assistants. Simple setup, powerful features.">
<style>
:root {
/* Enhanced color palette */
--bg-primary: #0a0a0a;
--bg-secondary: #141414;
--bg-tertiary: #1a1a1a;
--bg-code: #0d0d0d;
--text-primary: #e8e8e8;
--text-secondary: #999999;
--text-tertiary: #666666;
--accent: #00c896;
--accent-hover: #00b082;
--accent-muted: #00c89633;
--accent-alt: #ff7979;
--accent-alt-hover: #ff6b6b;
--border: #2a2a2a;
--border-subtle: #1f1f1f;
/* Typography scale */
--text-xs: 0.75rem;
--text-sm: 0.875rem;
--text-base: 1rem;
--text-lg: 1.333rem;
--text-xl: 1.777rem;
--text-2xl: 2.369rem;
--text-3xl: 3.157rem;
/* Spacing scale */
--space-2: 0.5rem;
--space-3: 0.75rem;
--space-4: 1rem;
--space-5: 1.5rem;
--space-6: 2rem;
--space-8: 3rem;
/* Animation */
--transition-base: 250ms;
--ease-out: cubic-bezier(0.16, 1, 0.3, 1);
}
* {
margin: 0;
padding: 0;
box-sizing: border-box;
}
body {
font-family: -apple-system, BlinkMacSystemFont, 'Inter', 'Segoe UI', 'Roboto', 'Ubuntu', sans-serif;
background-color: var(--bg-primary);
color: var(--text-primary);
font-size: var(--text-base);
line-height: 1.7;
letter-spacing: -0.011em;
-webkit-font-smoothing: antialiased;
min-height: 100vh;
background-image:
radial-gradient(circle at 10% 20%, rgba(0, 212, 170, 0.08) 0%, transparent 50%),
radial-gradient(circle at 80% 80%, rgba(255, 107, 107, 0.08) 0%, transparent 50%);
}
/* Subtle background texture */
body::before {
content: '';
position: fixed;
top: 0;
left: 0;
width: 100%;
height: 100%;
background-image:
repeating-linear-gradient(
0deg,
transparent,
transparent 2px,
rgba(255, 255, 255, 0.01) 2px,
rgba(255, 255, 255, 0.01) 4px
);
pointer-events: none;
z-index: 1;
}
.container {
max-width: 800px;
margin: 0 auto;
padding: var(--space-6) var(--space-5);
position: relative;
z-index: 2;
}
header {
text-align: center;
padding: var(--space-8) 0;
border-bottom: 1px solid var(--border);
margin-bottom: var(--space-8);
position: relative;
}
h1 {
font-size: var(--text-3xl);
font-weight: 300;
letter-spacing: -0.03em;
line-height: 1.1;
margin-bottom: var(--space-3);
color: var(--text-primary);
position: relative;
}
.tagline {
color: var(--text-secondary);
font-size: var(--text-lg);
margin-bottom: var(--space-5);
font-family: 'Cascadia Code', 'SF Mono', monospace;
}
.github-cta {
display: inline-flex;
align-items: center;
gap: var(--space-3);
background-color: var(--bg-secondary);
border: 2px solid var(--accent);
border-radius: 8px;
padding: var(--space-3) var(--space-5);
color: var(--text-primary);
text-decoration: none;
font-weight: 500;
transition: all var(--transition-base) var(--ease-out);
position: relative;
overflow: hidden;
backdrop-filter: blur(10px);
}
.github-cta::before {
content: '';
position: absolute;
top: 0;
left: -100%;
width: 100%;
height: 100%;
background: linear-gradient(90deg, transparent, rgba(0, 212, 170, 0.2), transparent);
transition: left 0.5s;
}
.github-cta:hover::before {
left: 100%;
}
.github-cta:hover {
transform: translateY(-2px) scale(1.02);
box-shadow: 0 4px 20px var(--accent-muted);
border-color: var(--accent-hover);
}
.compatibility {
background-color: var(--bg-secondary);
border: 1px solid var(--border);
border-radius: 8px;
padding: var(--space-4);
margin-bottom: var(--space-6);
text-align: center;
font-size: var(--text-sm);
position: relative;
overflow: hidden;
}
.compatibility::before {
content: '';
position: absolute;
top: -100%;
left: -100%;
width: 300%;
height: 300%;
background: linear-gradient(
45deg,
transparent 48%,
var(--accent-muted) 49%,
var(--accent-muted) 51%,
transparent 52%
);
animation: scan 8s linear infinite;
}
@keyframes scan {
0% { transform: translate(-30%, -30%); }
100% { transform: translate(30%, 30%); }
}
.compatibility strong {
color: var(--accent);
font-weight: 600;
}
section {
margin-bottom: var(--space-8);
}
.video-section {
margin: var(--space-8) 0;
}
.video-container {
position: relative;
width: 100%;
padding-bottom: 56.25%; /* 16:9 aspect ratio */
background-color: var(--bg-code);
border: 1px solid var(--border);
border-radius: 12px;
overflow: hidden;
box-shadow: 0 0 40px var(--accent-muted);
margin-top: var(--space-5);
}
.video-container::before {
content: '';
position: absolute;
top: -2px;
left: -2px;
right: -2px;
bottom: -2px;
background: linear-gradient(45deg, var(--accent), var(--accent-alt));
border-radius: 12px;
opacity: 0.5;
z-index: -1;
animation: pulse 4s ease-in-out infinite;
}
@keyframes pulse {
0%, 100% { opacity: 0.3; }
50% { opacity: 0.6; }
}
.video-container iframe {
position: absolute;
top: 0;
left: 0;
width: 100%;
height: 100%;
border-radius: 12px;
}
h2 {
font-size: var(--text-xl);
font-weight: 400;
margin-bottom: var(--space-4);
color: var(--accent);
position: relative;
}
p {
margin-bottom: var(--space-4);
color: var(--text-secondary);
line-height: 1.8;
}
.features {
display: grid;
gap: var(--space-5);
margin-top: var(--space-6);
}
.feature {
background-color: var(--bg-secondary);
padding: var(--space-5);
border-radius: 8px;
border: 1px solid var(--border);
transition: all var(--transition-base) var(--ease-out);
position: relative;
overflow: hidden;
}
.feature::before {
content: '';
position: absolute;
top: 0;
left: 0;
right: 0;
height: 1px;
background: linear-gradient(90deg, transparent, var(--accent), transparent);
transform: translateX(-100%);
transition: transform 0.5s;
}
.feature:hover::before {
transform: translateX(0);
}
.feature h3 {
font-size: var(--text-lg);
margin-bottom: var(--space-2);
color: var(--text-primary);
font-weight: 500;
}
.feature p {
font-size: var(--text-sm);
margin-bottom: 0;
line-height: 1.6;
}
.feature:hover {
border-color: var(--accent);
transform: translateX(4px);
box-shadow: 0 0 20px var(--accent-muted);
}
.code-block {
background-color: var(--bg-code);
border: 1px solid var(--border);
border-radius: 8px;
padding: var(--space-5);
margin: var(--space-5) 0;
overflow-x: auto;
font-family: 'Cascadia Code', 'SF Mono', 'Monaco', 'Inconsolata', monospace;
font-size: var(--text-sm);
line-height: 1.6;
position: relative;
box-shadow: inset 0 2px 4px rgba(0, 0, 0, 0.3);
}
.code-block code {
color: var(--text-primary);
display: block;
}
.comment {
color: var(--text-tertiary);
font-style: italic;
}
.typing-indicator {
display: inline-block;
width: 2px;
height: 1.2em;
background: linear-gradient(var(--accent), transparent);
animation: blink 1s infinite;
vertical-align: text-bottom;
margin-left: 2px;
}
@keyframes blink {
0%, 50% { opacity: 1; }
51%, 100% { opacity: 0; }
}
.highlight-box {
background-color: var(--bg-secondary);
border: 1px solid var(--border);
border-radius: 8px;
padding: var(--space-5);
margin: var(--space-6) 0;
position: relative;
}
.highlight-box h3 {
font-size: var(--text-lg);
margin-bottom: var(--space-3);
color: var(--text-primary);
display: flex;
align-items: center;
gap: var(--space-2);
}
.highlight-box .label {
background-color: var(--accent);
color: var(--bg-primary);
padding: 2px 8px;
border-radius: 4px;
font-size: var(--text-xs);
text-transform: uppercase;
letter-spacing: 0.05em;
font-weight: 600;
}
.highlight-box p {
margin-bottom: var(--space-3);
}
.highlight-box p a {
color: var(--accent);
text-decoration: none;
border-bottom: 1px dotted var(--accent);
transition: all var(--transition-base);
}
.highlight-box p a:hover {
color: var(--accent-hover);
border-bottom-style: solid;
}
.highlight-box .links {
display: flex;
gap: var(--space-4);
flex-wrap: wrap;
margin-top: var(--space-3);
}
.links {
display: flex;
gap: var(--space-6);
margin-top: var(--space-6);
flex-wrap: wrap;
}
.links a, .highlight-box a {
color: var(--accent);
text-decoration: none;
display: inline-flex;
align-items: center;
gap: var(--space-2);
transition: all var(--transition-base);
position: relative;
}
.links a::after, .highlight-box a::after {
content: '';
position: absolute;
bottom: -2px;
left: 0;
width: 0;
height: 1px;
background-color: var(--accent);
transition: width var(--transition-base) var(--ease-out);
}
.links a:hover::after, .highlight-box a:hover::after {
width: 100%;
}
.links a:hover, .highlight-box a:hover {
color: var(--accent-hover);
}
.requirements {
background-color: var(--bg-secondary);
border: 1px solid var(--border);
border-radius: 8px;
padding: var(--space-5);
margin: var(--space-6) 0;
position: relative;
}
.requirements::before {
content: 'SYSTEM REQUIREMENTS';
position: absolute;
top: -10px;
left: var(--space-4);
background-color: var(--bg-secondary);
padding: 0 var(--space-2);
color: var(--accent);
font-size: var(--text-xs);
font-family: 'Cascadia Code', monospace;
letter-spacing: 0.1em;
}
.requirements h3 {
margin-bottom: var(--space-4);
color: var(--text-primary);
font-weight: 500;
}
.requirements ul {
list-style: none;
color: var(--text-secondary);
}
.requirements li {
margin-bottom: var(--space-2);
padding-left: var(--space-5);
position: relative;
}
.requirements li::before {
content: 'āø';
position: absolute;
left: var(--space-2);
color: var(--accent);
}
footer {
margin-top: var(--space-8);
padding-top: var(--space-6);
border-top: 1px solid var(--border);
text-align: center;
color: var(--text-secondary);
font-size: var(--text-sm);
}
footer a {
color: var(--accent);
text-decoration: none;
}
footer a:hover {
text-decoration: underline;
}
/* Focus styles */
a:focus, button:focus {
outline: 2px solid var(--accent);
outline-offset: 2px;
}
/* Reduced motion */
@media (prefers-reduced-motion: reduce) {
*, *::before, *::after {
animation-duration: 0.01ms !important;
animation-iteration-count: 1 !important;
transition-duration: 0.01ms !important;
}
}
@media (max-width: 600px) {
h1 {
font-size: var(--text-2xl);
}
.container {
padding: var(--space-5) var(--space-4);
}
.links, .highlight-box .links {
flex-direction: column;
gap: var(--space-3);
}
.code-block {
font-size: var(--text-xs);
}
}
</style>
</head>
<body>
<div class="container">
<header>
<h1>VoiceMode MCP</h1>
<p class="tagline">"Voice Mode for Claude Code (and other AI Coding Assistants)"</p>
<a href="https://github.com/mbailey/voicemode" class="github-cta">
<svg width="20" height="20" viewBox="0 0 16 16" fill="currentColor">
<path d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0016 8c0-4.42-3.58-8-8-8z"/>
</svg>
View on GitHub
</a>
</header>
<div class="compatibility">
<strong>Runs on:</strong> Linux ā¢ macOS ā¢ Windows (WSL) | <strong>Python:</strong> 3.10+
</div>
<section>
<h2>Overview</h2>
<p>
VoiceMode MCP brings natural voice conversations Claude Code and other AI coding assistants.
Built on the Model Context Protocol (MCP), it provides a clean, reliable interface for adding voice capabilities
to your AI workflows.
</p>
</section>
<section class="video-section">
<h2>See It In Action</h2>
<div class="video-container">
<iframe
src="https://www.youtube.com/embed/cYdwOD_-dQc"
title="VoiceMode MCP Demo"
frameborder="0"
allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
allowfullscreen>
</iframe>
</div>
</section>
<section>
<h2>Quick Start<span class="typing-indicator"></span></h2>
<div class="code-block">
<span class="comment"># Install VoiceMode MCP python package and dependencies</span><br>
curl -LsSf https://astral.sh/uv/install.sh | sh<br>
uvx voice-mode-install<br><br>
<span class="comment"># Optional: Set OpenAI API key (backup if local services unavailable)</span><br>
export OPENAI_API_KEY=your-openai-key<br><br>
<span class="comment"># Add VoiceMode to Claude</span><br>
claude mcp add --scope user voicemode -- uvx --refresh voice-mode<br><br>
<span class="comment"># Start a voice conversation</span><br>
claude converse
</code>
</div>
<p style="margin-top: 1.5rem; color: var(--text-secondary);">
The voice-mode-install command automatically:
</p>
<ul style="list-style: none; color: var(--text-secondary); margin-left: 0;">
<li style="margin-bottom: 0.5rem; padding-left: 1.5rem; position: relative;">
<span style="position: absolute; left: 0; color: var(--accent);">ā</span>
Checks and installs system dependencies (PortAudio, FFmpeg, gcc, etc.)
</li>
<li style="margin-bottom: 0.5rem; padding-left: 1.5rem; position: relative;">
<span style="position: absolute; left: 0; color: var(--accent);">ā</span>
Installs VoiceMode MCP package via UV
</li>
<li style="margin-bottom: 0.5rem; padding-left: 1.5rem; position: relative;">
<span style="position: absolute; left: 0; color: var(--accent);">ā</span>
Configures shell completions for the voicemode CLI
</li>
<li style="margin-bottom: 0.5rem; padding-left: 1.5rem; position: relative;">
<span style="position: absolute; left: 0; color: var(--accent);">ā</span>
Sets up optional local STT/TTS services (Whisper, Kokoro)
</li>
<li style="margin-bottom: 0.5rem; padding-left: 1.5rem; position: relative;">
<span style="position: absolute; left: 0; color: var(--accent);">ā</span>
Validates the installation and provides next steps
</li>
</ul>
<p style="margin-top: 1.5rem; color: var(--text-secondary);">
For manual setup or detailed instructions, see the <a href="https://github.com/mbailey/voicemode/blob/main/docs/tutorials/getting-started.md" style="color: var(--accent); text-decoration: none; border-bottom: 1px dotted var(--accent);">Getting Started Guide</a>.
</p>
</section>
<div class="highlight-box">
<h3>
<span class="label">Optional</span>
Self-Hosted Voice Services
</h3>
<p>
For complete privacy, run speech recognition and text-to-speech locally instead of using OpenAI.
Both <a href="https://github.com/ggerganov/whisper.cpp">whisper.cpp</a> and <a href="https://github.com/remsky/Kokoro-FastAPI">Kokoro-FastAPI</a> provide OpenAI-compatible APIs for seamless integration.
</p>
<div class="code-block" style="margin-top: 1rem;">
<span class="comment"># Install local speech-to-text (Whisper)</span><br>
voicemode whisper install<br><br>
<span class="comment"># Install local text-to-speech (Kokoro)</span><br>
voicemode kokoro install
</div>
</div>
<section>
<h2>Features</h2>
<div class="features">
<div class="feature">
<h3>Voice Conversations</h3>
<p>Natural voice interactions with Claude through your microphone and speakers, airpods, etc</p>
</div>
<div class="feature">
<h3>OpenAI Compatible</h3>
<p>Works with OpenAI's API and compatible services for speech processing</p>
</div>
<div class="feature">
<h3>Simple Integration</h3>
<p>Clean MCP protocol implementation that works seamlessly with Claude Desktop</p>
</div>
</div>
</section>
<section>
<div class="requirements">
<h3>Requirements</h3>
<ul>
<li>OpenAI API key (or self-hosted STT & TTS services)</li>
<li>Microphone and speakers for voice I/O</li>
<li>Python 3.8+ (handled by uvx)</li>
</ul>
</div>
</section>
<section>
<h2>Resources</h2>
<div class="links">
<a href="https://github.com/mbailey/voicemode">
<svg width="20" height="20" viewBox="0 0 16 16" fill="currentColor">
<path d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0016 8c0-4.42-3.58-8-8-8z"/>
</svg>
GitHub Repository
</a>
<a href="https://pypi.org/project/voice-mode/">
<svg width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2">
<path d="M21 16V8a2 2 0 00-1-1.73l-7-4a2 2 0 00-2 0l-7 4A2 2 0 003 8v8a2 2 0 001 1.73l7 4a2 2 0 002 0l7-4A2 2 0 0021 16z"/>
<polyline points="3.27 6.96 12 12.01 20.73 6.96"/>
<line x1="12" y1="22.08" x2="12" y2="12"/>
</svg>
PyPI Package
</a>
<a href="https://github.com/mbailey/voicemode/issues">
<svg width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2">
<circle cx="12" cy="12" r="10"/>
<line x1="12" y1="8" x2="12" y2="12"/>
<line x1="12" y1="16" x2="12.01" y2="16"/>
</svg>
Report Issues
</a>
</div>
</section>
<footer>
<p>
<a href="https://getvoicemode.com">getvoicemode.com</a> · A <a href="https://failmode.com">Failmode</a> Project · MIT Licensed
</p>
</footer>
</div>
<!-- Goatcounter Analytics - Privacy-respecting, no cookies -->
<script data-goatcounter="https://getvoicemode.goatcounter.com/count"
async src="//gc.zgo.at/count.js"></script>
<noscript>
<img src="https://getvoicemode.goatcounter.com/count?p=/">
</noscript>
</body>
</html>