| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287 |
- #!/usr/bin/env node
- /**
- * tts-doubao.mjs · 豆包语音 TTS(火山引擎 openspeech)
- *
- * ⚠️ 可选云能力:本脚本会把待配音文本发送到字节跳动官方 TTS 接口(openspeech.bytedance.com),
- * 使用你自己的 key,endpoint 强制校验域名白名单。首次调用需 --yes 或 HUASHU_CLOUD_OK=1
- * 显式确认。数据流向声明见仓库根 SECURITY.md。
- *
- * 用法:
- * node scripts/cloud/tts-doubao.mjs --text "你好" --out demo.mp3 --yes
- * node scripts/cloud/tts-doubao.mjs --text-file script.txt --out out.mp3 --speed 1.0 --yes
- * node scripts/cloud/tts-doubao.mjs --text "你好" --out demo.mp3 --timestamps --yes # 附带字级时间戳
- *
- * 输出:
- * - mp3 文件写到 --out 路径
- * - stdout 打印一行 JSON: {"path":"...","duration":12.34,"bytes":54321}
- * - 带 --timestamps 时额外含 words: [{text,start,end,confidence}](秒,相对本段音频开头)
- * 注意:时间戳文本是 TN 后文本(如 "2025" 会变成 "二零二五"),标点附在前一个字上;
- * 需要 2.0 资源(seed-tts-2.0 / seed-icl-2.0),仅中英文。
- *
- * 依赖:Node 18+(自带 fetch/crypto)、ffprobe(测时长,brew install ffmpeg)
- *
- * env(自动从 skill 根目录 .env 读取,也可走 process.env 覆盖):
- * DOUBAO_TTS_API_KEY 可选(新版 API Key 鉴权)
- * DOUBAO_APP_ID 可选(控制台 App ID,与 DOUBAO_ACCESS_KEY 配套)
- * DOUBAO_ACCESS_KEY 可选(控制台 Access Token,与 DOUBAO_APP_ID 配套)
- * DOUBAO_TTS_VOICE_ID 必填(音色 id)
- * DOUBAO_TTS_RESOURCE_ID 可选(默认按音色自动推断)
- * DOUBAO_TTS_ENDPOINT 默认 https://openspeech.bytedance.com/api/v3/tts/unidirectional
- */
- import fs from 'node:fs';
- import path from 'node:path';
- import { execFileSync } from 'node:child_process';
- import { fileURLToPath } from 'node:url';
- import { randomUUID } from 'node:crypto';
- const __dirname = path.dirname(fileURLToPath(import.meta.url));
- const SKILL_ROOT = path.resolve(__dirname, '..', '..');
- function loadEnv() {
- const envPath = path.join(SKILL_ROOT, '.env');
- if (!fs.existsSync(envPath)) return;
- const text = fs.readFileSync(envPath, 'utf8');
- for (const line of text.split('\n')) {
- const trimmed = line.trim();
- if (!trimmed || trimmed.startsWith('#')) continue;
- const idx = trimmed.indexOf('=');
- if (idx < 0) continue;
- const key = trimmed.slice(0, idx).trim();
- let val = trimmed.slice(idx + 1).trim();
- if ((val.startsWith('"') && val.endsWith('"')) || (val.startsWith("'") && val.endsWith("'"))) {
- val = val.slice(1, -1);
- }
- if (!(key in process.env)) process.env[key] = val;
- }
- }
- loadEnv();
- function parseArgs(argv) {
- const args = { speed: '1.0', encoding: 'mp3' };
- for (let i = 2; i < argv.length; i++) {
- const a = argv[i];
- if (a === '--text') args.text = argv[++i];
- else if (a === '--text-file') args.textFile = argv[++i];
- else if (a === '--out') args.out = argv[++i];
- else if (a === '--speed') args.speed = argv[++i];
- else if (a === '--voice') args.voice = argv[++i];
- else if (a === '--encoding') args.encoding = argv[++i];
- else if (a === '--timestamps') args.timestamps = true;
- else if (a === '--yes') args.yes = true;
- else if (a === '--help' || a === '-h') args.help = true;
- }
- return args;
- }
- function usage() {
- console.error(`
- tts-doubao.mjs · 豆包语音 TTS
- --text <str> 要合成的文本
- --text-file <path> 从文件读取文本(与 --text 二选一)
- --out <path> 输出 mp3 路径(必填)
- --speed <float> 语速倍率,默认 1.0(0.5-2.0)
- --voice <voice_id> 覆盖 .env 里的音色 id
- --encoding <ext> mp3 / wav / pcm,默认 mp3
- --timestamps 请求字级时间戳(enable_subtitle),结果 JSON 多一个 words 数组
- --yes 确认将文本发送到豆包 TTS 官方接口(或设 HUASHU_CLOUD_OK=1)
- `.trim());
- process.exit(1);
- }
- function getDuration(filePath) {
- try {
- const out = execFileSync('ffprobe', [
- '-v', 'error',
- '-show_entries', 'format=duration',
- '-of', 'default=noprint_wrappers=1:nokey=1',
- filePath,
- ], { encoding: 'utf8' });
- return parseFloat(out.trim());
- } catch (e) {
- return null;
- }
- }
- function inferResourceId(voiceId) {
- // 复刻音色默认走 2.0:本账号只开通了 seed-icl-2.0(1.0 会 403 resource not granted),
- // 且字级时间戳(enable_subtitle)只有 2.0 资源支持。
- if (voiceId.startsWith('S_')) return 'seed-icl-2.0';
- if (voiceId.includes('uranus')) return 'seed-tts-2.0';
- return 'seed-tts-1.0';
- }
- function speedToSpeechRate(speed) {
- const ratio = parseFloat(speed);
- if (!Number.isFinite(ratio)) return 0;
- return Math.max(-50, Math.min(100, Math.round((ratio - 1) * 100)));
- }
- function buildAuthHeaders({ requestId, resourceId }) {
- const apiKey = process.env.DOUBAO_TTS_API_KEY;
- const appId = process.env.DOUBAO_APP_ID;
- const accessKey = process.env.DOUBAO_ACCESS_KEY;
- const headers = {
- 'Content-Type': 'application/json',
- 'X-Api-Resource-Id': resourceId,
- 'X-Api-Request-Id': requestId,
- };
- if (apiKey) {
- headers['X-Api-Key'] = apiKey;
- return headers;
- }
- if (!appId) throw new Error('缺 DOUBAO_TTS_API_KEY 或 DOUBAO_APP_ID(检查 .env)');
- if (!accessKey) throw new Error('缺 DOUBAO_ACCESS_KEY(检查 .env)');
- headers['X-Api-App-Id'] = appId;
- headers['X-Api-Access-Key'] = accessKey;
- return headers;
- }
- async function readV3Audio(res) {
- const text = await res.text();
- const chunks = [];
- const words = []; // 字级时间戳(enable_subtitle 开启时服务端按句返回 sentence.words)
- let finalCode = null;
- let finalMessage = '';
- for (const line of text.split(/\r?\n/)) {
- const trimmed = line.trim();
- if (!trimmed) continue;
- let json;
- try {
- json = JSON.parse(trimmed);
- } catch (e) {
- throw new Error(`API 响应行不是 JSON:${trimmed.slice(0, 200)}`);
- }
- const code = json.code ?? 0;
- if (code === 20000000) {
- finalCode = code;
- finalMessage = json.message || '';
- break;
- }
- if (code !== 0) {
- throw new Error(`API 返回错误 code=${code} msg=${json.message || JSON.stringify(json)}`);
- }
- if (json.data) chunks.push(Buffer.from(json.data, 'base64'));
- if (json.sentence && Array.isArray(json.sentence.words)) {
- for (const w of json.sentence.words) {
- words.push({
- text: w.word,
- start: w.startTime,
- end: w.endTime,
- confidence: w.confidence,
- });
- }
- }
- }
- if (!chunks.length) {
- const detail = finalCode ? `结束码 ${finalCode} ${finalMessage}` : text.slice(0, 500);
- throw new Error(`API 响应无音频数据:${detail}`);
- }
- return { audio: Buffer.concat(chunks), words };
- }
- // endpoint 域名白名单:key 和文本只允许发往字节官方域名,防 .env 被篡改后重定向
- const ALLOWED_ENDPOINT_HOSTS = /(^|\.)(bytedance\.com|volces\.com)$/;
- async function tts({ text, voice, speed, encoding, timestamps }) {
- const endpoint = process.env.DOUBAO_TTS_ENDPOINT || 'https://openspeech.bytedance.com/api/v3/tts/unidirectional';
- const host = new URL(endpoint).hostname;
- if (!ALLOWED_ENDPOINT_HOSTS.test(host)) {
- throw new Error(`DOUBAO_TTS_ENDPOINT 域名 ${host} 不在白名单(*.bytedance.com / *.volces.com),拒绝发送`);
- }
- const voiceId = voice || process.env.DOUBAO_TTS_VOICE_ID || process.env.DOUBAO_SPEAKER;
- const resourceId = process.env.DOUBAO_TTS_RESOURCE_ID || inferResourceId(voiceId || '');
- const requestId = randomUUID();
- if (!voiceId) throw new Error('缺 DOUBAO_TTS_VOICE_ID(检查 .env 或用 --voice 传)');
- const body = {
- user: { uid: 'huashu-design' },
- req_params: {
- text,
- speaker: voiceId,
- audio_params: {
- format: encoding,
- sample_rate: 24000,
- speech_rate: speedToSpeechRate(speed),
- // 字级时间戳:仅 2.0 资源(seed-tts-2.0 / seed-icl-2.0)支持,中英文 only
- ...(timestamps ? { enable_subtitle: true } : {}),
- },
- },
- };
- const res = await fetch(endpoint, {
- method: 'POST',
- headers: buildAuthHeaders({ requestId, resourceId }),
- body: JSON.stringify(body),
- });
- if (!res.ok) {
- const errText = await res.text();
- throw new Error(`HTTP ${res.status}: ${errText.slice(0, 500)}`);
- }
- return readV3Audio(res);
- }
- async function main() {
- const args = parseArgs(process.argv);
- if (args.help) usage();
- let text = args.text;
- if (!text && args.textFile) {
- text = fs.readFileSync(args.textFile, 'utf8').trim();
- }
- if (!text) {
- console.error('错:缺 --text 或 --text-file');
- usage();
- }
- if (!args.out) {
- console.error('错:缺 --out');
- usage();
- }
- if (!args.yes && process.env.HUASHU_CLOUD_OK !== '1') {
- const host = new URL(process.env.DOUBAO_TTS_ENDPOINT || 'https://openspeech.bytedance.com').hostname;
- console.error(
- `[云能力确认] 本次将把约${text.length}字文本发送到 ${host}(豆包TTS官方接口,使用你自己的key合成语音)。\n` +
- `确认无误请重跑并加 --yes,或设置环境变量 HUASHU_CLOUD_OK=1。数据流向声明见 SECURITY.md。`,
- );
- process.exit(2);
- }
- const outPath = path.resolve(args.out);
- fs.mkdirSync(path.dirname(outPath), { recursive: true });
- const { audio, words } = await tts({
- text,
- voice: args.voice,
- speed: args.speed,
- encoding: args.encoding,
- timestamps: args.timestamps,
- });
- fs.writeFileSync(outPath, audio);
- const duration = getDuration(outPath);
- const result = {
- path: outPath,
- bytes: audio.length,
- duration,
- text_chars: text.length,
- };
- if (args.timestamps) result.words = words;
- console.log(JSON.stringify(result));
- }
- main().catch((err) => {
- console.error(`TTS 失败:${err.message}`);
- process.exit(1);
- });
|