whisper-speech-to-text
Version:
A JavaScript library enabling in-browser audio recording and transcription using OpenAI's Whisper Speech-to-Text
190 lines (189 loc) • 9.33 kB
JavaScript
"use strict";
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
return new (P || (P = Promise))(function (resolve, reject) {
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
step((generator = generator.apply(thisArg, _arguments || [])).next());
});
};
var __generator = (this && this.__generator) || function (thisArg, body) {
var _ = { label: 0, sent: function() { if (t[0] & 1) throw t[1]; return t[1]; }, trys: [], ops: [] }, f, y, t, g;
return g = { next: verb(0), "throw": verb(1), "return": verb(2) }, typeof Symbol === "function" && (g[Symbol.iterator] = function() { return this; }), g;
function verb(n) { return function (v) { return step([n, v]); }; }
function step(op) {
if (f) throw new TypeError("Generator is already executing.");
while (g && (g = 0, op[0] && (_ = 0)), _) try {
if (f = 1, y && (t = op[0] & 2 ? y["return"] : op[0] ? y["throw"] || ((t = y["return"]) && t.call(y), 0) : y.next) && !(t = t.call(y, op[1])).done) return t;
if (y = 0, t) op = [op[0] & 2, t.value];
switch (op[0]) {
case 0: case 1: t = op; break;
case 4: _.label++; return { value: op[1], done: false };
case 5: _.label++; y = op[1]; op = [0]; continue;
case 7: op = _.ops.pop(); _.trys.pop(); continue;
default:
if (!(t = _.trys, t = t.length > 0 && t[t.length - 1]) && (op[0] === 6 || op[0] === 2)) { _ = 0; continue; }
if (op[0] === 3 && (!t || (op[1] > t[0] && op[1] < t[3]))) { _.label = op[1]; break; }
if (op[0] === 6 && _.label < t[1]) { _.label = t[1]; t = op; break; }
if (t && _.label < t[2]) { _.label = t[2]; _.ops.push(op); break; }
if (t[2]) _.ops.pop();
_.trys.pop(); continue;
}
op = body.call(thisArg, _);
} catch (e) { op = [6, e]; y = 0; } finally { f = t = 0; }
if (op[0] & 5) throw op[1]; return { value: op[0] ? op[1] : void 0, done: true };
}
};
var __importDefault = (this && this.__importDefault) || function (mod) {
return (mod && mod.__esModule) ? mod : { "default": mod };
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.WhisperSTT = void 0;
var recordrtc_1 = require("recordrtc");
var axios_1 = __importDefault(require("axios"));
var AUDIO_TYPE = 'audio';
var MODEL = 'whisper-1';
var TRANSCRIPTIONS_API_URL = 'https://api.openai.com/v1/audio/transcriptions';
var WhisperSTT = /** @class */ (function () {
function WhisperSTT(apiKey) {
var _this = this;
this.pauseRecording = function () { return __awaiter(_this, void 0, void 0, function () {
return __generator(this, function (_a) {
switch (_a.label) {
case 0:
if (!this.recorder) {
throw new Error('Cannot pause recording: no recorder');
}
return [4 /*yield*/, this.recorder.pauseRecording()];
case 1:
_a.sent();
this.isPaused = true;
this.isRecording = false;
return [2 /*return*/];
}
});
}); };
this.resumeRecording = function () { return __awaiter(_this, void 0, void 0, function () {
return __generator(this, function (_a) {
switch (_a.label) {
case 0:
if (!this.recorder) {
throw new Error('Cannot resume recording: no recorder');
}
return [4 /*yield*/, this.recorder.resumeRecording()];
case 1:
_a.sent();
this.isPaused = false;
this.isRecording = true;
return [2 /*return*/];
}
});
}); };
this.startRecording = function () { return __awaiter(_this, void 0, void 0, function () {
var _a, error_1;
return __generator(this, function (_b) {
switch (_b.label) {
case 0:
_b.trys.push([0, 2, , 3]);
_a = this;
return [4 /*yield*/, navigator.mediaDevices.getUserMedia({ audio: true })];
case 1:
_a.stream = _b.sent();
this.recorder = new recordrtc_1.RecordRTCPromisesHandler(this.stream, {
type: AUDIO_TYPE,
});
this.recorder.startRecording();
this.isRecording = true;
this.isStopped = false;
return [3 /*break*/, 3];
case 2:
error_1 = _b.sent();
this.isRecording = false;
this.isStopped = true;
throw new Error("Error starting recording: ".concat(error_1.message));
case 3: return [2 /*return*/];
}
});
}); };
this.stopRecording = function (onFinish) { return __awaiter(_this, void 0, void 0, function () {
var blob, error_2;
var _a;
return __generator(this, function (_b) {
switch (_b.label) {
case 0:
if (!this.isRecording || !this.recorder) {
throw new Error('Cannot stop recording: no recorder');
}
_b.label = 1;
case 1:
_b.trys.push([1, 4, , 5]);
return [4 /*yield*/, this.recorder.stopRecording()];
case 2:
_b.sent();
return [4 /*yield*/, this.recorder.getBlob()];
case 3:
blob = _b.sent();
this.transcribe(blob, onFinish);
(_a = this.stream) === null || _a === void 0 ? void 0 : _a.getTracks().forEach(function (track) {
track.stop();
});
this.recorder = null;
this.stream = null;
this.isRecording = false;
this.isStopped = true;
this.isPaused = false;
return [3 /*break*/, 5];
case 4:
error_2 = _b.sent();
this.isRecording = false;
this.isStopped = true;
throw new Error("Error stopping recording: ".concat(error_2.message));
case 5: return [2 /*return*/];
}
});
}); };
this.transcribe = function (audioBlob, onFinish) { return __awaiter(_this, void 0, void 0, function () {
var formData, headers, response, error_3;
var _a;
return __generator(this, function (_b) {
switch (_b.label) {
case 0:
formData = new FormData();
formData.append('file', audioBlob, 'audio.wav');
formData.append('model', MODEL);
headers = {
Authorization: "Bearer ".concat(this.apiKey),
'Content-Type': 'multipart/form-data',
};
_b.label = 1;
case 1:
_b.trys.push([1, 3, , 4]);
return [4 /*yield*/, axios_1.default.post(TRANSCRIPTIONS_API_URL, formData, {
headers: headers,
})];
case 2:
response = _b.sent();
onFinish(((_a = response.data) === null || _a === void 0 ? void 0 : _a.text) || '');
return [3 /*break*/, 4];
case 3:
error_3 = _b.sent();
console.error('Error transcribing audio:', error_3);
return [3 /*break*/, 4];
case 4: return [2 /*return*/];
}
});
}); };
this.recorder = null;
this.stream = null;
this.isRecording = false;
this.isStopped = true;
this.isPaused = false;
if (!apiKey) {
throw new Error('API key is required');
}
this.apiKey = apiKey;
}
return WhisperSTT;
}());
exports.WhisperSTT = WhisperSTT;