@fonoster/apiserver 0.7.23 → 0.7.24

package/dist/core/seed.js

@@ -93,6 +93,16 @@ function main() {
                 type: "ASSISTANT"
             }
         });
+        yield prisma.product.upsert({
+            where: { ref: "tts.azure" },
+            update: {},
+            create: {
+                ref: "tts.azure",
+                name: "Azure Text-to-Speech",
+                vendor: "MICROSOFT",
+                type: "TTS"
+            }
+        });
     });
 }
 main()

package/dist/voice/tts/Azure.d.ts

@@ -1,5 +1,4 @@
 import { Readable } from "stream";
-import * as sdk from "microsoft-cognitiveservices-speech-sdk";
 import * as z from "zod";
 import { AbstractTextToSpeech } from "./AbstractTextToSpeech";
 import { SynthOptions } from "./types";
@@ -21,12 +20,7 @@ declare class Azure extends AbstractTextToSpeech<typeof ENGINE_NAME> {
         ref: string;
         stream: Readable;
     }>;
-    doSynthesize(params: {
-        text: string;
-        speechConfig: sdk.SpeechConfig;
-        isSSML?: boolean;
-    }): Promise<unknown>;
-    getConfigValidationSchema(): z.Schema;
-    getCredentialsValidationSchema(): z.Schema;
+    static getConfigValidationSchema(): z.Schema;
+    static getCredentialsValidationSchema(): z.Schema;
 }
 export { Azure, ENGINE_NAME };

package/dist/voice/tts/Azure.js

@@ -61,7 +61,6 @@ const isSsml_1 = require("./isSsml");
 const ENGINE_NAME = "tts.azure";
 exports.ENGINE_NAME = ENGINE_NAME;
 const logger = (0, logger_1.getLogger)({ service: "apiserver", filePath: __filename });
-// XXX: Must re-implement to provide an id an a Readable stream
 class Azure extends AbstractTextToSpeech_1.AbstractTextToSpeech {
     constructor(config) {
         super();
@@ -78,44 +77,36 @@ class Azure extends AbstractTextToSpeech_1.AbstractTextToSpeech {
             speechConfig.speechSynthesisVoiceName = options.voice;
             speechConfig.speechSynthesisOutputFormat =
                 sdk.SpeechSynthesisOutputFormat.Riff16Khz16BitMonoPcm;
-            yield this.doSynthesize({
-                text,
-                speechConfig,
-                isSSML: (0, isSsml_1.isSsml)(text)
-            });
-            const ref = this.createMediaReference();
-            // TODO: Fix this placeholder
-            return { ref, stream: new stream_1.Readable() };
-        });
-    }
-    doSynthesize(params) {
-        return __awaiter(this, void 0, void 0, function* () {
-            const { text, speechConfig } = params;
             const synthesizer = new sdk.SpeechSynthesizer(speechConfig);
-            // FIXME: Let's turn this into constants
-            const func = params.isSSML ? "speakSsmlAsync" : "speakTextAsync";
-            return new Promise((resolve, reject) => {
-                synthesizer[func](text, function (result) {
+            const isSSML = (0, isSsml_1.isSsml)(text);
+            const func = isSSML ? "speakSsmlAsync" : "speakTextAsync";
+            const audioData = yield new Promise((resolve, reject) => {
+                const audioChunks = [];
+                synthesizer[func](text, (result) => {
                     if (result.reason === sdk.ResultReason.SynthesizingAudioCompleted) {
-                        resolve("");
+                        audioChunks.push(Buffer.from(result.audioData));
+                        resolve(Buffer.concat(audioChunks));
                     }
                     else {
-                        reject(new Error("speech synthesis canceled: " + result.errorDetails));
+                        reject(new Error("Speech synthesis canceled: " + result.errorDetails));
                     }
                     synthesizer.close();
-                }, function (err) {
+                }, (err) => {
                     synthesizer.close();
                     reject(new Error(err));
                 });
             });
+            const ref = this.createMediaReference();
+            const stream = stream_1.Readable.from(audioData);
+            return { ref, stream };
         });
     }
-    getConfigValidationSchema() {
+    static getConfigValidationSchema() {
         return z.object({
             voice: z.nativeEnum(common_1.AzureVoice)
         });
     }
-    getCredentialsValidationSchema() {
+    static getCredentialsValidationSchema() {
         return z.object({
             subscriptionKey: z.string(),
             serviceRegion: z.string()

package/dist/voice/tts/Deepgram.js

@@ -33,6 +33,25 @@ var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, ge
 };
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.ENGINE_NAME = exports.Deepgram = void 0;
+/*
+ * Copyright (C) 2024 by Fonoster Inc (https://fonoster.com)
+ * http://github.com/fonoster/fonoster
+ *
+ * This file is part of Fonoster
+ *
+ * Licensed under the MIT License (the "License");
+ * you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *    https://opensource.org/licenses/MIT
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+const stream_1 = require("stream");
 const common_1 = require("@fonoster/common");
 const logger_1 = require("@fonoster/logger");
 const z = __importStar(require("zod"));
@@ -65,8 +84,7 @@ class Deepgram extends AbstractTextToSpeech_1.AbstractTextToSpeech {
                 container: "none"
             });
             const ref = this.createMediaReference();
-            // TODO: Needs testing
-            return { ref, stream: yield response.getStream() };
+            return { ref, stream: stream_1.Readable.from(yield response.getStream()) };
         });
     }
     static getConfigValidationSchema() {

package/dist/voice/tts/Google.js

@@ -88,10 +88,9 @@ class Google extends AbstractTextToSpeech_1.AbstractTextToSpeech {
                     name: voice
                 }
             };
-            yield this.client.synthesizeSpeech(request);
+            const [response] = yield this.client.synthesizeSpeech(request);
             const ref = this.createMediaReference();
-            // TODO: Fix this placeholder
-            return { ref, stream: new stream_1.Readable() };
+            return { ref, stream: stream_1.Readable.from(response.audioContent) };
         });
     }
     static getConfigValidationSchema() {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@fonoster/apiserver",
-  "version": "0.7.23",
+  "version": "0.7.24",
   "description": "APIServer for Fonoster",
   "author": "Pedro Sanders <psanders@fonoster.com>",
   "homepage": "https://github.com/fonoster/fonoster#readme",
@@ -72,5 +72,5 @@
     "@types/uuid": "^9.0.8",
     "@types/validator": "^13.12.0"
   },
-  "gitHead": "eaf6ffdfdaaed15b6077f36b0aaa529d5eed8048"
+  "gitHead": "58b141dc01f99f0aa903cad5497d12cd474f79df"
 }