kemuriririn's picture
update
a528625
{% extends "base.html" %}
{% block title %}About - Voice Clone Arena{% endblock %}
{% block current_page %}About{% endblock %}
{% block extra_head %}
<style>
.about-container {
max-width: 800px;
margin: 0 auto;
}
.about-section {
background: white;
border-radius: var(--radius);
padding: 24px;
margin-bottom: 24px;
box-shadow: var(--shadow);
}
.about-section h2 {
color: var(--primary-color);
margin-bottom: 16px;
font-size: 24px;
}
.about-section p {
margin-bottom: 16px;
line-height: 1.6;
color: #444;
}
.about-section p:last-child {
margin-bottom: 0;
}
.feature-list {
list-style: none;
padding: 0;
}
.feature-list li {
margin-bottom: 12px;
padding-left: 28px;
position: relative;
}
.feature-list li::before {
content: "•";
color: var(--primary-color);
font-size: 24px;
position: absolute;
left: 8px;
top: -4px;
}
.credits-list {
display: grid;
grid-template-columns: repeat(auto-fill, minmax(300px, 1fr));
gap: 24px;
margin-top: 16px;
}
.credit-item {
display: flex;
align-items: center;
justify-content: space-between;
padding-bottom: 8px;
border-bottom: 1px solid var(--border-color);
}
.credit-item a {
color: var(--primary-color);
text-decoration: none;
}
.credit-item a:hover {
text-decoration: underline;
}
.social-links {
display: flex;
gap: 12px;
}
.social-icon {
width: 20px;
height: 20px;
}
.citation-box {
background-color: var(--light-gray);
border-radius: var(--radius);
padding: 16px;
margin-top: 16px;
position: relative;
font-family: monospace;
white-space: pre-wrap;
word-break: break-word;
font-size: 14px;
line-height: 1.5;
}
.copy-citation {
position: absolute;
top: 8px;
right: 8px;
background-color: white;
border: 1px solid var(--border-color);
border-radius: var(--radius);
width: 36px;
height: 36px;
display: flex;
align-items: center;
justify-content: center;
cursor: pointer;
transition: background-color 0.2s;
}
.copy-citation:hover {
background-color: var(--light-gray);
}
.copy-citation svg {
color: var(--text-color);
}
.faq-item {
margin-bottom: 20px;
}
.faq-question {
font-weight: 600;
margin-bottom: 8px;
color: var(--primary-color);
}
.faq-answer {
line-height: 1.6;
}
/* Dark mode styles */
@media (prefers-color-scheme: dark) {
.about-section {
background-color: var(--light-gray);
border-color: var(--border-color);
}
.about-section p {
color: var(--text-color);
}
.citation-box {
background-color: var(--secondary-color);
border-color: var(--border-color);
}
.copy-citation {
background-color: var(--light-gray);
border-color: var(--border-color);
}
.copy-citation:hover {
background-color: rgba(255, 255, 255, 0.1);
}
.copy-citation svg {
color: var(--text-color);
}
.faq-question {
color: var(--primary-color);
}
.social-icon.icon-x {
filter: invert(1);
}
}
</style>
{% endblock %}
{% block content %}
<div class="about-container">
<div class="about-section">
<h2>Welcome to Voice Clone Arena</h2>
<p>
Voice Clone Arena evaluates leading speech synthesis models in an interactive, community-driven platform.
Inspired by LMsys's <a href="https://chat.lmsys.org/" target="_blank" rel="noopener">Chatbot Arena</a>, we've created
a space where anyone can compare and rank text-to-speech technologies through direct, side-by-side evaluation.
</p>
<p>
Our second version now supports conversational models for podcast-like content generation, expanding the arena's scope to reflect the diverse applications of modern speech synthesis.
</p>
</div>
<div class="about-section">
<h2>Motivation</h2>
<p>
The field of speech synthesis has long lacked reliable methods to measure model quality. Traditional
metrics like WER (word error rate) often fail to capture the nuances of natural speech, while subjective
measures such as MOS (mean opinion score) typically involve small-scale experiments with limited participants.
</p>
<p>
Voice Clone Arena addresses these limitations by inviting the entire community to participate in the evaluation
process, making both the opportunity to rank models and the resulting insights accessible to everyone.
</p>
</div>
<div class="about-section">
<h2>How The Arena Works</h2>
<p>
The concept is straightforward: enter text that will be synthesized by two competing models. After
listening to both samples, vote for the one that sounds more natural and engaging. To prevent bias,
model names are revealed only after your vote is submitted.
</p>
<ul class="feature-list">
<li>Enter your own text or select a random sentence</li>
<li>Listen to two different TTS models synthesize the same content</li>
<li>Compare conversational models for podcast-like content</li>
<li>Vote for the model that sounds more natural, clear, and expressive</li>
<li>Track model rankings on our leaderboard</li>
</ul>
</div>
<div class="about-section">
<h2>Frequently Asked Questions</h2>
<div class="faq-item">
<div class="faq-question">What happened to the Voice Clone Arena V1 leaderboard?</div>
<div class="faq-answer">
The Voice Clone Arena V1 leaderboard is now deprecated. While you can no longer vote on it, the results and leaderboard are still available for reference at <a href="https://huggingface.co/spaces/TTS-AGI/TTS-Arena" target="_blank" rel="noopener">Voice Clone Arena V1</a>. The leaderboard is static and will not change.
</div>
</div>
<div class="faq-item">
<div class="faq-question">How are models ranked in Voice Clone Arena?</div>
<div class="faq-answer">
Models are ranked using an Elo rating system, similar to chess rankings. When you vote for a model, its rating increases while the other model's rating decreases. The amount of change depends on the current ratings of both models.
</div>
</div>
<div class="faq-item">
<div class="faq-question">Is the Voice Clone Arena V2 leaderboard affected by votes from V1?</div>
<div class="faq-answer">
No, the Voice Clone Arena V2 leaderboard is a completely fresh start. Votes from V1 do not affect the V2 leaderboard in any way. All models in V2 start with a clean slate.
</div>
</div>
<div class="faq-item">
<div class="faq-question">Can I suggest a model to be added to the arena?</div>
<div class="faq-answer">
Yes! We welcome suggestions for new models. Please reach out to us through the Hugging Face community or create an issue in our GitHub repository. If you are developing a new model and wish for it to be added anonymously for pre-release evaluation, please <a href="mailto:[email protected]" target="_blank" rel="noopener">reach out to us to discuss</a>.
</div>
</div>
<div class="faq-item">
<div class="faq-question">How can I contribute to the project?</div>
<div class="faq-answer">
You can contribute by voting on models, suggesting improvements, reporting bugs, or even contributing code. Check our GitHub repository for more information on how to get involved.
</div>
</div>
<div class="faq-item">
<div class="faq-question">What's new in Voice Clone Arena 2.0?</div>
<div class="faq-answer">
Voice Clone Arena 2.0 introduces support for conversational models (for podcast-like content), improved UI/UX, and a more robust backend infrastructure for handling more models and votes.
</div>
</div>
<div class="faq-item">
<div class="faq-question">Do I need to login to use Voice Clone Arena?</div>
<div class="faq-answer">
Login is optional and not required to vote. If you choose to login (with Hugging Face), texts you enter will be associated with your account, and you'll have access to a personal leaderboard showing the models you favor the most.
</div>
</div>
</div>
<div class="about-section">
<h2>Citation</h2>
<p>
If you use Voice Clone Arena in your research, please cite it as follows:
</p>
<div class="citation-box" id="citation-text">@misc{voice-clone-arena,
title = {Voice Clone Arena: Benchmarking Voice Clone Models in the Wild},
author = {kemuriririn},
year = 2025,
publisher = {Hugging Face},
howpublished = "\url{https://huggingface.co/spaces/kemuriririn/Voice-Clone-Arena}"
}<button class="copy-citation" onclick="copyToClipboard()" title="Copy citation"><svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-copy-icon lucide-copy"><rect width="14" height="14" x="8" y="8" rx="2" ry="2"/><path d="M4 16c-1.1 0-2-.9-2-2V4c0-1.1.9-2 2-2h10c1.1 0 2 .9 2 2"/></svg></button></div>
<script>
function copyToClipboard() {
const text = document.getElementById('citation-text').innerText;
navigator.clipboard.writeText(text).then(() => {
const btn = document.querySelector('.copy-citation');
const originalContent = btn.innerHTML;
btn.innerHTML = '<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M20 6 9 17l-5-5"/></svg>';
setTimeout(() => {
btn.innerHTML = originalContent;
}, 2000);
});
}
</script>
</div>
<div class="about-section">
<h2>Privacy Statement</h2>
<p>
We may store text you enter and generated audio. If you are logged in, we may associate your votes with your Hugging Face username.
You agree that we may collect, share, and/or publish any data you input for research and/or
commercial purposes.
</p>
</div>
<div class="about-section">
<h2>License</h2>
<p>
Generated audio clips cannot be redistributed and may be used for personal, non-commercial use only.
The code for the Arena is licensed under the Zlib license.
Random sentences are sourced from a filtered subset of the
<a href="https://www.cs.columbia.edu/~hgs/audio/harvard.html" target="_blank" rel="noopener">Harvard Sentences</a>.
</p>
</div>
</div>
{% endblock %}