From c455b4ed4383456244076e40e8b8428780e60fe0 Mon Sep 17 00:00:00 2001
From: "russell@unturf.com" <russell@unturf.com>
Date: Tue, 27 Jan 2026 16:48:07 -0500
Subject: [PATCH] Rewrite engine descriptions: lead with capabilities, not
 model names

---
 public/text-to-speech.html | 59 +++++++++++++-------------------------
 1 file changed, 20 insertions(+), 39 deletions(-)

diff --git a/public/text-to-speech.html b/public/text-to-speech.html
index e0339d7..d247bea 100644
--- a/public/text-to-speech.html
+++ b/public/text-to-speech.html
@@ -108,7 +108,7 @@
         <ul>
             <li><strong>Zero API Keys:</strong> No registration, no tracking, no rate limits on your own infrastructure</li>
             <li><strong>OpenAI-Compatible:</strong> Drop-in replacement - change one URL and you're running</li>
-            <li><strong>Five TTS Engines:</strong> Qwen3-TTS (default, voice cloning), Piper (fast), XTTS (quality), Silero (CPU-friendly), Kokoro (lightweight)</li>
+            <li><strong>Five TTS Engines:</strong> Voice cloning (default), fast synthesis, HD cloning, multilingual CPU, and lightweight edge</li>
             <li><strong>42+ Built-In Cloned Voices:</strong> With 10-language support including Chinese, Japanese, Korean, and European languages</li>
             <li><strong>Self-Hostable:</strong> Docker compose, Makefile-driven, runs on your hardware</li>
             <li><strong>AGPL v3 Licensed:</strong> Keeps TTS libre forever - even network service users get source code</li>
@@ -169,13 +169,17 @@ client.audio.speech.create(
 
         <h3 id="discover-voices">Discover Voices</h3>
 
-        <p>Browse all available voices with engine metadata: <a href="https://speech.ai.unturf.com/v1/voices" target="_blank"><code>speech.ai.unturf.com/v1/voices</code></a></p>
+        <p>Every voice has a name, a gender, and a personality. Browse the full catalog live — the API tells you exactly what's available and which engine powers each one.</p>
+
+        <p><a href="https://speech.ai.unturf.com/v1/voices" target="_blank"><strong>→ See all voices</strong></a></p>
 
         <pre><code class="bash">curl https://speech.ai.unturf.com/v1/voices | jq .</code></pre>
 
         <h3 id="discover-models">Discover Models</h3>
 
-        <p>See all available TTS engines: <a href="https://speech.ai.unturf.com/v1/models" target="_blank"><code>speech.ai.unturf.com/v1/models</code></a></p>
+        <p>Five engines, each with different strengths. Query the API to see what's running on any instance — useful when self-hosting to verify your setup.</p>
+
+        <p><a href="https://speech.ai.unturf.com/v1/models" target="_blank"><strong>→ See all engines</strong></a></p>
 
         <pre><code class="bash">curl https://speech.ai.unturf.com/v1/models | jq .</code></pre>
 
@@ -221,46 +225,23 @@ make hydrate</code></pre>
 
         <h2 id="the-engines">The Five Engines</h2>
 
-        <h3 id="qwen">🧠 Qwen3-TTS (tts-1-qwen) — Default</h3>
-        <ul>
-            <li><strong>Quality:</strong> State-of-the-art voice cloning from 3-second samples</li>
-            <li><strong>Languages:</strong> 10 languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian)</li>
-            <li><strong>Voices:</strong> 42+ built-in cloned voices (aria, clara, elena, atlas, caleb, felix, and <a href="https://speech.ai.unturf.com/v1/voices" target="_blank">more</a>)</li>
-            <li><strong>Use Case:</strong> Default engine for all TTS — high quality with fast 97ms first-packet latency</li>
-            <li><strong>Tech:</strong> 1.7B params, Apache 2.0 license, actively maintained by Alibaba</li>
-        </ul>
+        <p>Each engine has a different personality. You don't need to think about model names — just pick a voice and we route it to the right engine. But if you're curious what's under the hood:</p>
 
-        <h3 id="piper">🏃 Piper TTS (tts-1)</h3>
-        <ul>
-            <li><strong>Speed:</strong> Real-time on CPU (fastest)</li>
-            <li><strong>Voices:</strong> 100+ English voices via LibriTTS</li>
-            <li><strong>Use Case:</strong> High-volume, low-latency synthesis</li>
-            <li><strong>Tech:</strong> ONNX runtime, 22.05kHz output</li>
-        </ul>
+        <h3 id="qwen">🧠 Voice Cloning — <small>Default Engine</small></h3>
+        <p>Our default engine clones real human voices from 3-second audio samples. 42+ distinct speakers, each with their own timbre, cadence, and character. Speaks 10 languages natively — English, Chinese, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian. First audio arrives in under 100ms.</p>
+        <p><a href="https://speech.ai.unturf.com/v1/voices" target="_blank"><strong>→ Browse all 42+ voices</strong></a></p>
 
-        <h3 id="xtts">🎙️ XTTS v2 (tts-1-hd)</h3>
-        <ul>
-            <li><strong>Quality:</strong> Voice cloning from 6-second samples</li>
-            <li><strong>Languages:</strong> 16 languages with auto-detection</li>
-            <li><strong>Use Case:</strong> Custom voices, audiobooks, high-quality synthesis</li>
-            <li><strong>Tech:</strong> Coqui TTS, requires ~4GB GPU VRAM</li>
-        </ul>
+        <h3 id="piper">🏃 Fast Synthesis</h3>
+        <p>When you need speed over everything else. Runs entirely on CPU, no GPU required. 100+ English voices. Ideal for high-volume batch jobs or real-time applications where latency matters more than naturalness.</p>
 
-        <h3 id="silero">⚡ Silero TTS (tts-1-silero)</h3>
-        <ul>
-            <li><strong>Speed:</strong> Real-time CPU inference</li>
-            <li><strong>Voices:</strong> 148 voices across 5 languages (English, Russian, German, Spanish, French)</li>
-            <li><strong>Use Case:</strong> CPU-only servers, multilingual applications</li>
-            <li><strong>Tech:</strong> PyTorch, 48kHz output, actively maintained</li>
-        </ul>
+        <h3 id="xtts">🎙️ HD Voice Cloning</h3>
+        <p>Clone any voice from a 6-second sample. Supports 16 languages with automatic detection. The highest fidelity option — great for audiobooks, character voices, or when you want to sound like yourself. Needs a GPU with ~4GB VRAM.</p>
 
-        <h3 id="kokoro">🪶 Kokoro TTS (tts-1-kokoro)</h3>
-        <ul>
-            <li><strong>Architecture:</strong> Lightweight decoder-only (82M params)</li>
-            <li><strong>Voices:</strong> 34 intentionally OpenAI-themed voices (American/British English)</li>
-            <li><strong>Use Case:</strong> Edge devices, low-resource environments</li>
-            <li><strong>Tech:</strong> Apache 2.0 license, 24kHz output</li>
-        </ul>
+        <h3 id="silero">⚡ Multilingual CPU</h3>
+        <p>148 voices across 5 languages (English, Russian, German, Spanish, French) — all running on CPU. The go-to choice when you need multilingual support without a GPU. Clean 48kHz output, actively maintained.</p>
+
+        <h3 id="kokoro">🪶 Lightweight</h3>
+        <p>A tiny 82M parameter model that punches above its weight. 34 voices in American and British English. Built for edge devices, embedded systems, and anywhere resources are tight. Apache 2.0 licensed.</p>
 
         <h2 id="get-involved">Get Involved</h2>