examples/mp3.html · BinWoo/TalkingHead

代码拉取完成,页面将自动刷新

扫描微信二维码支付

取消

支付完成

richgiteeai

Watch

不关注关注所有动态仅关注版本发行动态关注但不提醒动态

1 Star 0 Fork 0

BinWoo/TalkingHead

代码 Issues 0 Pull Requests 0 Wiki 统计流水线

服务

加入 Gitee

与超过 1400万开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)

免费加入

已有帐号? 立即登录

文件

main

分支 (1)

标签 (6)

管理

main

v1.2.3

v1.2.2

v1.2.1

v1.2.0

v1.1.0

v1.0.0

克隆/下载

HTTPS SSH SVN SVN+SSH 下载ZIP

提示

下载代码请复制以下命令到终端执行

为确保你提交的代码身份被 Gitee 正确识别,请执行以下命令完成配置

git config --global user.name userName 
git config --global user.email userEmail

初次使用 SSH 协议进行代码克隆、推送等操作时,需按下述提示完成 SSH 配置

1 生成 RSA 密钥

2 获取 RSA 公钥内容,并配置到 SSH公钥中

在 Gitee 上使用 SVN,请访问使用指南

使用 HTTPS 协议时,命令行会出现如下账号密码验证步骤。基于安全考虑,Gitee 建议配置并使用私人令牌替代登录密码进行克隆、推送等操作

Username for 'https://gitee.com': userName

Password for 'https://userName@gitee.com': # 私人令牌

分支 1

标签 6

TalkingHead

examples

mp3.html

mp3.html 6.09 KB

<!DOCTYPE html>
<html>
<head>
 <title>Talking Head - MP3 example</title>

let head; // TalkingHead instance
 let audio; // Audio object

// Make a transcription of an audio file using OpenAI's Whisper API
 async function loadAudio(file) {

try {
 const nodeJSON = document.getElementById('json');
 nodeJSON.value = "Please wait...";

const nodePlay = document.getElementById('play');
 nodePlay.disabled = true;

// OpenAI Whisper request
 const form = new FormData();
 form.append("file", file);
 form.append("model", "whisper-1");
 form.append("language", "en");
 form.append("response_format", "verbose_json" );
 form.append("timestamp_granularities[]", "word" );
 form.append("timestamp_granularities[]", "segment" );

// NOTE: Never put your API key in a client-side code unless you know
 // that you are the only one to have access to that code!
 const response = await fetch( "https://api.openai.com/v1/audio/transcriptions" , {
 method: "POST",
 body: form,
 headers: {
 "Authorization": "Bearer <add-your-openai-api-key-here>" // <- Change this
 }
 });

if ( response.ok ) {

const json = await response.json();
 nodeJSON.value = JSON.stringify(json, null, 4);

// Fetch audio
 if ( json.words && json.words.length ) {

var reader = new FileReader();
 reader.readAsArrayBuffer(file);

reader.onload = async readerEvent => {
 let arraybuffer = readerEvent.target.result;
 let audiobuffer = await head.audioCtx.decodeAudioData(arraybuffer);

// TalkingHead audio object
 audio = {
 audio: audiobuffer,
 words: [],
 wtimes: [],
 wdurations: [],
 markers: [],
 mtimes: []
 };

// Add words to the audio object
 json.words.forEach( x => {
 audio.words.push( x.word );
 audio.wtimes.push( 1000 * x.start - 150 );
 audio.wdurations.push( 1000 * (x.end - x.start) );
 });

// Callback function to make the avatar look at the camera
 const startSegment = async () => {
 head.lookAtCamera(500);
 head.speakWithHands();
 };

// Add timed callback markers to the audio object
 json.segments.forEach( x => {
 if ( x.start > 2 && x.text.length > 10 ) {
 audio.markers.push( startSegment );
 audio.mtimes.push( 1000 * x.start - 1000 );
 }
 });

// Enable play button
 nodePlay.disabled = false;
 }
 }

} else {
 nodeJSON.value = 'Error: ' + response.status + ' ' + response.statusText;
 console.log(response);
 }

} catch (error) {
 console.log(error);
 }
 }

document.addEventListener('DOMContentLoaded', async function(e) {

// Instantiate the class
 // NOTE: Text-to-speech not initialized
 const nodeAvatar = document.getElementById('avatar');
 head = new TalkingHead( nodeAvatar, {
 ttsEndpoint: "https://eu-texttospeech.googleapis.com/v1beta1/text:synthesize",
 lipsyncModules: ["en", "fi"],
 cameraView: "head"
 });

// Load and show the avatar
 const nodeLoading = document.getElementById('loading');
 try {
 await head.showAvatar( {
 url: 'https://models.readyplayer.me/64bfa15f0e72c63d7c3934a6.glb?morphTargets=ARKit,Oculus+Visemes,mouthOpen,mouthSmile,eyesClosed,eyesLookUp,eyesLookDown&textureSizeLimit=1024&textureFormat=png',
 body: 'F',
 avatarMood: 'neutral',
 lipsyncLang: 'en'
 }, (ev) => {
 if ( ev.lengthComputable ) {
 let val = Math.min(100,Math.round(ev.loaded/ev.total * 100 ));
 nodeLoading.textContent = "Loading " + val + "%";
 }
 });
 nodeLoading.style.display = 'none';
 } catch (error) {
 console.log(error);
 nodeLoading.textContent = error.toString();
 }

// File changed
 const nodeLoad = document.getElementById('load');
 nodeLoad.addEventListener('change', function(ev) {
 let file = ev.target.files[0];
 loadAudio(file);
 });

// Play button clicked
 const nodePlay = document.getElementById('play');
 nodePlay.addEventListener('click', function() {
 if ( audio ) {
 head.speakAudio( audio );
 }
 });

});

</script>
</head>

</html>

一键复制编辑原始数据按行查看历史

met4citizen 提交于 2024年06月14日 15:50 +08:00 . Updated to use v1.2

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184

<!DOCTYPE html>
<html>
<head>
 <title>Talking Head - MP3 example</title>

 <style>
 body, html { width:100%; height:100%; margin: 0; padding: 0; background-color: dimgray; color: white; }
 #avatar { display: block; position: absolute; top: 0; left: 0; right: 40%; bottom: 0; }
 #controls { display: flex; flex-direction: column; gap: 10px; position: absolute; top: 50px; left: Calc( 60% + 50px); right: 50px; bottom: 50px; }
 #load { font-family: Arial; font-size: 20px; }
 #json { flex: 1; background-color: lightgray; font-family: Arial; font-size: 20px; }
 #play { font-family: Arial; font-size: 20px; }
 #loading { display: block; position: absolute; top: 50px; left: 50px; width: 200px; font-family: Arial; font-size: 20px; }
 </style>

 <script type="importmap">
 { "imports":
 {
 "three": "https://cdn.jsdelivr.net/npm/three@0.161.0/build/three.module.js/+esm",
 "three/addons/": "https://cdn.jsdelivr.net/npm/three@0.161.0/examples/jsm/",
 "talkinghead": "https://cdn.jsdelivr.net/gh/met4citizen/TalkingHead@1.2/modules/talkinghead.mjs"
 }
 }
 </script>

 <script type="module">
 import { TalkingHead } from "talkinghead";

 let head; // TalkingHead instance
 let audio; // Audio object

 // Make a transcription of an audio file using OpenAI's Whisper API
 async function loadAudio(file) {

 try {
 const nodeJSON = document.getElementById('json');
 nodeJSON.value = "Please wait...";

 const nodePlay = document.getElementById('play');
 nodePlay.disabled = true;

 // OpenAI Whisper request
 const form = new FormData();
 form.append("file", file);
 form.append("model", "whisper-1");
 form.append("language", "en");
 form.append("response_format", "verbose_json" );
 form.append("timestamp_granularities[]", "word" );
 form.append("timestamp_granularities[]", "segment" );

 // NOTE: Never put your API key in a client-side code unless you know
 // that you are the only one to have access to that code!
 const response = await fetch( "https://api.openai.com/v1/audio/transcriptions" , {
 method: "POST",
 body: form,
 headers: {
 "Authorization": "Bearer <add-your-openai-api-key-here>" // <- Change this
 }
 });

 if ( response.ok ) {

 const json = await response.json();
 nodeJSON.value = JSON.stringify(json, null, 4);

 // Fetch audio
 if ( json.words && json.words.length ) {

 var reader = new FileReader();
 reader.readAsArrayBuffer(file);

 reader.onload = async readerEvent => {
 let arraybuffer = readerEvent.target.result;
 let audiobuffer = await head.audioCtx.decodeAudioData(arraybuffer);

 // TalkingHead audio object
 audio = {
 audio: audiobuffer,
 words: [],
 wtimes: [],
 wdurations: [],
 markers: [],
 mtimes: []
 };

 // Add words to the audio object
 json.words.forEach( x => {
 audio.words.push( x.word );
 audio.wtimes.push( 1000 * x.start - 150 );
 audio.wdurations.push( 1000 * (x.end - x.start) );
 });


 // Callback function to make the avatar look at the camera
 const startSegment = async () => {
 head.lookAtCamera(500);
 head.speakWithHands();
 };

 // Add timed callback markers to the audio object
 json.segments.forEach( x => {
 if ( x.start > 2 && x.text.length > 10 ) {
 audio.markers.push( startSegment );
 audio.mtimes.push( 1000 * x.start - 1000 );
 }
 });

 // Enable play button
 nodePlay.disabled = false;
 }
 }

 } else {
 nodeJSON.value = 'Error: ' + response.status + '' + response.statusText;
 console.log(response);
 }

 } catch (error) {
 console.log(error);
 }
 }

 document.addEventListener('DOMContentLoaded', async function(e) {

 // Instantiate the class
 // NOTE: Text-to-speech not initialized
 const nodeAvatar = document.getElementById('avatar');
 head = new TalkingHead( nodeAvatar, {
 ttsEndpoint: "https://eu-texttospeech.googleapis.com/v1beta1/text:synthesize",
 lipsyncModules: ["en", "fi"],
 cameraView: "head"
 });

 // Load and show the avatar
 const nodeLoading = document.getElementById('loading');
 try {
 await head.showAvatar( {
 url: 'https://models.readyplayer.me/64bfa15f0e72c63d7c3934a6.glb?morphTargets=ARKit,Oculus+Visemes,mouthOpen,mouthSmile,eyesClosed,eyesLookUp,eyesLookDown&textureSizeLimit=1024&textureFormat=png',
 body: 'F',
 avatarMood: 'neutral',
 lipsyncLang: 'en'
 }, (ev) => {
 if ( ev.lengthComputable ) {
 let val = Math.min(100,Math.round(ev.loaded/ev.total * 100 ));
 nodeLoading.textContent = "Loading " + val + "%";
 }
 });
 nodeLoading.style.display = 'none';
 } catch (error) {
 console.log(error);
 nodeLoading.textContent = error.toString();
 }

 // File changed
 const nodeLoad = document.getElementById('load');
 nodeLoad.addEventListener('change', function(ev) {
 let file = ev.target.files[0];
 loadAudio(file);
 });

 // Play button clicked
 const nodePlay = document.getElementById('play');
 nodePlay.addEventListener('click', function() {
 if ( audio ) {
 head.speakAudio( audio );
 }
 });

 });

 </script>
</head>

<body>
 <div id="avatar"></div>
 <div id="controls">
 <input id="load" type="file" accept=".m4a,.mp3,.webm,.mp4,.mpga,.wav,.mpeg">
 <textarea id="json" readonly></textarea>
 <input id="play" type="button" value="Play" disabled="disable">
 </div>
 <div id="loading"></div>
</body>

</html>