coze-plugin-utils
Version:
Comprehensive utility library for Coze plugins with multimedia processing, browser automation, cloud storage integration, and AI-powered video/audio generation capabilities
120 lines • 5.22 kB
JavaScript
;
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
if (k2 === undefined) k2 = k;
var desc = Object.getOwnPropertyDescriptor(m, k);
if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
desc = { enumerable: true, get: function() { return m[k]; } };
}
Object.defineProperty(o, k2, desc);
}) : (function(o, m, k, k2) {
if (k2 === undefined) k2 = k;
o[k2] = m[k];
}));
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
Object.defineProperty(o, "default", { enumerable: true, value: v });
}) : function(o, v) {
o["default"] = v;
});
var __importStar = (this && this.__importStar) || (function () {
var ownKeys = function(o) {
ownKeys = Object.getOwnPropertyNames || function (o) {
var ar = [];
for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
return ar;
};
return ownKeys(o);
};
return function (mod) {
if (mod && mod.__esModule) return mod;
var result = {};
if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
__setModuleDefault(result, mod);
return result;
};
})();
var __importDefault = (this && this.__importDefault) || function (mod) {
return (mod && mod.__esModule) ? mod : { "default": mod };
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.tts = tts;
const core_1 = require("../core");
const sdk = __importStar(require("microsoft-cognitiveservices-speech-sdk"));
const node_path_1 = __importDefault(require("node:path"));
const promises_1 = __importDefault(require("node:fs/promises"));
async function tts({ voiceName, text, withFrontend = false, speed = 1.0, pitch = 0, volumn = 1.0, }) {
const azureConfig = (0, core_1.getGlobalConfig)('azure');
if (!azureConfig || !azureConfig.speech) {
throw new Error('Azure Speech Service is not configured');
}
const { key, region } = azureConfig.speech;
const speechConfig = sdk.SpeechConfig.fromSubscription(key, region);
const matches = /^\w+-\w+/.exec(voiceName);
const lang = matches ? matches[0] : 'en-US';
speechConfig.speechSynthesisVoiceName = voiceName;
speechConfig.speechRecognitionLanguage = lang;
speechConfig.speechSynthesisOutputFormat = sdk.SpeechSynthesisOutputFormat.Audio48Khz192KBitRateMonoMp3;
const synthesizer = new sdk.SpeechSynthesizer(speechConfig);
function formatProsody(speed, volumn, pitch) {
const format = (v) => {
let ret = `${Math.round((v - 1) * 100)}%`;
if (!ret.startsWith('-'))
ret = `+${ret}`;
return ret;
};
return `speed="${format(speed)}" pitch="${format(pitch)}" volumn="${format(volumn)}"`;
}
let xml = `<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xml:lang="${lang}">
<voice name="${voiceName}"><lang xml:lang="${lang}">
<prosody ${formatProsody(speed, volumn, pitch)}>${text}</prosody>
</lang></voice></speak>
`;
if (lang !== 'zh-CN') {
const chineseCharactersReg = /[\u4e00-\u9fa5]+/;
xml = xml.replace(chineseCharactersReg, '<lang xml:lang="zh-CN">“$&”</lang>');
}
let frontend;
if (withFrontend) {
frontend = {
words: [],
};
let index = 0;
synthesizer.wordBoundary = (sender, event) => {
let _text = event.text;
_text = _text.replace(/<[^>]*?>/g, '').trim();
// 忽略可能多余的标点符号
const _index = text.slice(index).indexOf(_text);
if (_index === -1)
return;
const textOffset = _index + index;
index = textOffset + _text.length;
frontend.words.push({
audioOffset: event.audioOffset / 10000,
text: event.text,
textOffset,
duration: event.duration / 10000,
boundaryType: event.boundaryType,
});
};
}
const audioData = await new Promise((resolve, reject) => {
synthesizer.speakSsmlAsync(xml, (result) => {
if (result.reason === sdk.ResultReason.SynthesizingAudioCompleted) {
// console.log('synthesis finished.');
// console.log(result);
resolve({ data: result.audioData, duration: result.privAudioDuration / 1e7 });
}
else {
// console.error(result);
reject(new Error('SynthesizingAudioFailed'));
}
}, (_error) => {
// console.error('Error:', error);
reject(new Error('SynthesizingAudioFailed'));
});
});
const tmpDir = await (0, core_1.createTempDir)();
const audioPath = node_path_1.default.join(tmpDir, 'speech.mp3');
await promises_1.default.writeFile(audioPath, Buffer.from(audioData.data));
return { audio: audioPath, duration: audioData.duration, frontend };
}
//# sourceMappingURL=azure.speech.js.map