add speed parameter

web/README.md

@@ -4,6 +4,8 @@ This example demonstrates how to use Supertonic in a web browser using ONNX Runt
 
 ## 📰 Update News
 
+**2025.11.19** - Added speed control slider to adjust speech synthesis speed (default: 1.05, recommended range: 0.9-1.5).
+
 **2025.11.19** - Added automatic text chunking for long-form inference. Long texts are split into chunks and synthesized with natural pauses.
 
 ## Features

web/helper.js

@@ -72,7 +72,7 @@ export class TextToSpeech {
         this.sampleRate = cfgs.ae.sample_rate;
     }
 
-    async _infer(textList, style, totalStep, progressCallback = null) {
+    async _infer(textList, style, totalStep, speed = 1.05, progressCallback = null) {
         const bsz = textList.length;
         
         // Process text
@@ -94,6 +94,11 @@ export class TextToSpeech {
         });
         const duration = Array.from(dpOutputs.duration.data);
         
+        // Apply speed factor to duration
+        for (let i = 0; i < duration.length; i++) {
+            duration[i] /= speed;
+        }
+        
         // Encode text
         const textEncOutputs = await this.textEncOrt.run({
             text_ids: textIdsTensor,
@@ -176,7 +181,7 @@ export class TextToSpeech {
         return { wav, duration };
     }
 
-    async call(text, style, totalStep, silenceDuration = 0.3, progressCallback = null) {
+    async call(text, style, totalStep, speed = 1.05, silenceDuration = 0.3, progressCallback = null) {
         if (style.ttl.dims[0] !== 1) {
             throw new Error('Single speaker text to speech only supports single style');
         }
@@ -185,7 +190,7 @@ export class TextToSpeech {
         let durCat = 0;
         
         for (const chunk of textList) {
-            const { wav, duration } = await this._infer([chunk], style, totalStep, progressCallback);
+            const { wav, duration } = await this._infer([chunk], style, totalStep, speed, progressCallback);
             
             if (wavCat.length === 0) {
                 wavCat = wav;
@@ -201,8 +206,8 @@ export class TextToSpeech {
         return { wav: wavCat, duration: [durCat] };
     }
 
-    async batch(textList, style, totalStep, progressCallback = null) {
-        return await this._infer(textList, style, totalStep, progressCallback);
+    async batch(textList, style, totalStep, speed = 1.05, progressCallback = null) {
+        return await this._infer(textList, style, totalStep, speed, progressCallback);
     }
 
     sampleNoisyLatent(duration, sampleRate, baseChunkSize, chunkCompress, latentDim) {

web/index.html

@@ -48,6 +48,12 @@
                             <input type="number" id="totalStep" value="5"
                                 min="1" max="50">
                         </div>
+                        
+                        <div class="section">
+                            <label for="speed">Speed (0.9-1.5 recommended):</label>
+                            <input type="number" id="speed" value="1.05"
+                                min="0.5" max="2.0" step="0.05">
+                        </div>
 
                     </div>
 

web/main.js

@@ -25,6 +25,7 @@ const textInput = document.getElementById('text');
 const voiceStyleSelect = document.getElementById('voiceStyleSelect');
 const voiceStyleInfo = document.getElementById('voiceStyleInfo');
 const totalStepInput = document.getElementById('totalStep');
+const speedInput = document.getElementById('speed');
 const generateBtn = document.getElementById('generateBtn');
 const statusBox = document.getElementById('statusBox');
 const statusText = document.getElementById('statusText');
@@ -186,6 +187,7 @@ async function generateSpeech() {
         `;
         
         const totalStep = parseInt(totalStepInput.value);
+        const speed = parseFloat(speedInput.value);
         
         showStatus('ℹ️ <strong>Generating speech from text...</strong>');
         const tic = Date.now();
@@ -194,6 +196,7 @@ async function generateSpeech() {
             text, 
             currentStyle, 
             totalStep,
+            speed,
             0.3,
             (step, total) => {
                 showStatus(`ℹ️ <strong>Denoising (${step}/${total})...</strong>`);