0.1.19

add language to playht3.0

lib/synth-audio.js

@@ -20,7 +20,8 @@ const {
   createKryptonClient,
   createRivaClient,
   noopLogger,
-  makeFilePath
+  makeFilePath,
+  makePlayhtKey
 } = require('./utils');
 const getNuanceAccessToken = require('./get-nuance-access-token');
 const getVerbioAccessToken = require('./get-verbio-token');
@@ -244,7 +245,7 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
         });
         break;
       case 'playht':
-        audioBuffer = await synthPlayHT(logger, {
+        audioBuffer = await synthPlayHT(client, logger, {
           credentials, options, stats, language, voice, text, renderForCaching, disableTtsStreaming, filePath
         });
         break;
@@ -755,12 +756,40 @@ const synthElevenlabs = async(logger, {
   }
 };
 
-const synthPlayHT = async(logger, {
-  credentials, options, stats, voice, text, renderForCaching, disableTtsStreaming
+const synthPlayHT = async(client, logger, {
+  credentials, options, stats, voice, language, text, renderForCaching, disableTtsStreaming
 }) => {
   const {api_key, user_id, voice_engine, options: credOpts} = credentials;
   const opts = !!options && Object.keys(options).length !== 0 ? options : JSON.parse(credOpts || '{}');
 
+  let synthesizeUrl = 'https://api.play.ht/api/v2/tts/stream';
+
+  // If model is play3.0, the synthesizeUrl is got from authentication endpoint
+  if (voice_engine === 'Play3.0') {
+    try {
+      const post = bent('https://api.play.ht', 'POST', 'json', 201, {
+        'AUTHORIZATION': api_key,
+        'X-USER-ID': user_id,
+        'Accept': 'application/json'
+      });
+      const key = makePlayhtKey(api_key);
+      const url = await client.get(key);
+      if (!url) {
+        const {inference_address, expires_at_ms} = await post('/api/v3/auth');
+        synthesizeUrl = inference_address;
+        const expiry =  Math.floor((expires_at_ms - Date.now()) / 1000 - 30);
+        await client.set(key, inference_address, 'EX', expiry);
+      } else {
+        // Use cached URL
+        synthesizeUrl = url;
+      }
+    } catch (err) {
+      logger.info({err}, 'synth PlayHT returned error for authentication version 3.0');
+      stats.increment('tts.count', ['vendor:playht', 'accepted:no']);
+      throw err;
+    }
+  }
+
   /* default to using the streaming interface, unless disabled by env var OR we want just a cache file */
   if (!JAMBONES_DISABLE_TTS_STREAMING && !renderForCaching && !disableTtsStreaming) {
     let params = '';
@@ -769,7 +798,9 @@ const synthPlayHT = async(logger, {
     params += ',vendor=playht';
     params += `,voice=${voice}`;
     params += `,voice_engine=${voice_engine}`;
+    params += `,synthesize_url=${synthesizeUrl}`;
     params += ',write_cache_file=1';
+    params += `,language=${language}`;
     if (opts.quality) params += `,quality=${opts.quality}`;
     if (opts.speed) params += `,speed=${opts.speed}`;
     if (opts.seed) params += `,style=${opts.seed}`;
@@ -778,6 +809,8 @@ const synthPlayHT = async(logger, {
     if (opts.voice_guidance) params += `,voice_guidance=${opts.voice_guidance}`;
     if (opts.style_guidance) params += `,style_guidance=${opts.style_guidance}`;
     if (opts.text_guidance) params += `,text_guidance=${opts.text_guidance}`;
+    if (opts.top_p) params += `,top_p=${opts.top_p}`;
+    if (opts.repetition_penalty) params += `,repetition_penalty=${opts.repetition_penalty}`;
     params += '}';
 
     return {
@@ -788,14 +821,18 @@ const synthPlayHT = async(logger, {
   }
 
   try {
-    const post = bent('https://api.play.ht', 'POST', 'buffer', {
-      'AUTHORIZATION': api_key,
-      'X-USER-ID': user_id,
+    const post = bent('POST', 'buffer', {
+      ...(voice_engine !== 'Play3.0' && {
+        'AUTHORIZATION': api_key,
+        'X-USER-ID': user_id,
+      }),
       'Accept': 'audio/mpeg',
       'Content-Type': 'application/json'
     });
-    const mp3 = await post('/api/v2/tts/stream', {
+
+    const mp3 = await post(synthesizeUrl, {
       text,
+      ...(voice_engine === 'Play3.0' && { language }),
       voice,
       voice_engine,
       output_format: 'mp3',

lib/utils.js

@@ -48,16 +48,25 @@ function getFileExtension({vendor, renderForCaching = false}) {
     case 'deepgram':
     case 'elevenlabs':
     case 'rimlabs':
-      if (!renderForCaching && !JAMBONES_DISABLE_TTS_STREAMING) {
-        return r8Extension;
-      } else {
+    case 'playht':
+      if (renderForCaching || JAMBONES_DISABLE_TTS_STREAMING) {
         return mp3Extension;
+      } else {
+        return r8Extension;
       }
     case 'nuance':
     case 'nvidia':
     case 'verbio':
       return r8Extension;
     default:
+      // If vendor is custom
+      if (vendor.startsWith('custom')) {
+        if (renderForCaching || JAMBONES_DISABLE_TTS_STREAMING) {
+          return mp3Extension;
+        } else {
+          return r8Extension;
+        }
+      }
       return mp3Extension;
   }
 }
@@ -89,6 +98,11 @@ function makeAwsKey(awsAccessKeyId) {
   return `aws:${hash.digest('hex')}`;
 }
 
+function makePlayhtKey(apiKey) {
+  const hash = crypto.createHash('sha1');
+  hash.update(apiKey);
+  return `playht:${hash.digest('hex')}`;
+}
 function makeVerbioKey(client_id) {
   const hash = crypto.createHash('sha1');
   hash.update(client_id);
@@ -162,6 +176,7 @@ module.exports = {
   makeSynthKey,
   makeNuanceKey,
   makeIbmKey,
+  makePlayhtKey,
   makeAwsKey,
   makeVerbioKey,
   getNuanceAccessToken,

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@jambonz/speech-utils",
-  "version": "0.1.15",
+  "version": "0.1.19",
   "lockfileVersion": 2,
   "requires": true,
   "packages": {
     "": {
       "name": "@jambonz/speech-utils",
-      "version": "0.1.15",
+      "version": "0.1.19",
       "license": "MIT",
       "dependencies": {
         "@aws-sdk/client-polly": "^3.496.0",
@@ -20,7 +20,7 @@
         "google-protobuf": "^3.21.2",
         "ibm-watson": "^8.0.0",
         "microsoft-cognitiveservices-speech-sdk": "1.38.0",
-        "openai": "^4.53.2",
+        "openai": "^4.25.0",
         "undici": "^6.4.0"
       },
       "devDependencies": {
@@ -2585,6 +2585,11 @@
       "integrity": "sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw==",
       "dev": true
     },
+    "node_modules/base-64": {
+      "version": "0.1.0",
+      "resolved": "https://registry.npmjs.org/base-64/-/base-64-0.1.0.tgz",
+      "integrity": "sha512-Y5gU45svrR5tI2Vt/X9GPd3L0HNIKzGu202EjxrXMpuc2V2CiKgemAbUUsqYmZJvPtCXoUKjNZwBJzsNScUbXA=="
+    },
     "node_modules/base64-js": {
       "version": "1.5.1",
       "resolved": "https://registry.npmjs.org/base64-js/-/base64-js-1.5.1.tgz",
@@ -2821,6 +2826,14 @@
         "url": "https://github.com/chalk/chalk?sponsor=1"
       }
     },
+    "node_modules/charenc": {
+      "version": "0.0.2",
+      "resolved": "https://registry.npmjs.org/charenc/-/charenc-0.0.2.tgz",
+      "integrity": "sha512-yrLQ/yVUFXkzg7EDQsPieE/53+0RlaWTs+wBrvW36cyilJ2SaDWfl4Yj7MtLTXleV9uEKefbAGUPv2/iWSooRA==",
+      "engines": {
+        "node": "*"
+      }
+    },
     "node_modules/clean-stack": {
       "version": "2.2.0",
       "resolved": "https://registry.npmjs.org/clean-stack/-/clean-stack-2.2.0.tgz",
@@ -2922,6 +2935,14 @@
         "node": ">= 8"
       }
     },
+    "node_modules/crypt": {
+      "version": "0.0.2",
+      "resolved": "https://registry.npmjs.org/crypt/-/crypt-0.0.2.tgz",
+      "integrity": "sha512-mCxBlsHFYh9C+HVpiEacem8FEBnMXgU9gy4zmNC+SXAZNB/1idgp/aulFJ4FgCi7GPEVbfyng092GqL2k2rmow==",
+      "engines": {
+        "node": "*"
+      }
+    },
     "node_modules/d": {
       "version": "1.0.1",
       "resolved": "https://registry.npmjs.org/d/-/d-1.0.1.tgz",
@@ -3076,6 +3097,15 @@
         "node": ">= 10.14.2"
       }
     },
+    "node_modules/digest-fetch": {
+      "version": "1.3.0",
+      "resolved": "https://registry.npmjs.org/digest-fetch/-/digest-fetch-1.3.0.tgz",
+      "integrity": "sha512-CGJuv6iKNM7QyZlM2T3sPAdZWd/p9zQiRNS9G+9COUCwzWFTs0Xp8NF5iePx7wtvhDykReiRRrSeNb4oMmB8lA==",
+      "dependencies": {
+        "base-64": "^0.1.0",
+        "md5": "^2.3.0"
+      }
+    },
     "node_modules/dotenv": {
       "version": "6.2.0",
       "resolved": "https://registry.npmjs.org/dotenv/-/dotenv-6.2.0.tgz",
@@ -4526,6 +4556,11 @@
         "url": "https://github.com/sponsors/ljharb"
       }
     },
+    "node_modules/is-buffer": {
+      "version": "1.1.6",
+      "resolved": "https://registry.npmjs.org/is-buffer/-/is-buffer-1.1.6.tgz",
+      "integrity": "sha512-NcdALwpXkTm5Zvvbk7owOUSvVvBKDgKP5/ewfXEznmQFfs4ZRmanOeKBTjRVjka3QFoN6XJ+9F3USqfHqTaU5w=="
+    },
     "node_modules/is-callable": {
       "version": "1.2.7",
       "resolved": "https://registry.npmjs.org/is-callable/-/is-callable-1.2.7.tgz",
@@ -5256,6 +5291,16 @@
         "semver": "bin/semver.js"
       }
     },
+    "node_modules/md5": {
+      "version": "2.3.0",
+      "resolved": "https://registry.npmjs.org/md5/-/md5-2.3.0.tgz",
+      "integrity": "sha512-T1GITYmFaKuO91vxyoQMFETst+O71VUPEU3ze5GNzDm0OWdP8v1ziTaAEPUr/3kLsY3Sftgz242A1SetQiDL7g==",
+      "dependencies": {
+        "charenc": "0.0.2",
+        "crypt": "0.0.2",
+        "is-buffer": "~1.1.6"
+      }
+    },
     "node_modules/micromatch": {
       "version": "4.0.5",
       "resolved": "https://registry.npmjs.org/micromatch/-/micromatch-4.0.5.tgz",
@@ -5710,18 +5755,19 @@
       }
     },
     "node_modules/openai": {
-      "version": "4.53.2",
-      "resolved": "https://registry.npmjs.org/openai/-/openai-4.53.2.tgz",
-      "integrity": "sha512-ohYEv6OV3jsFGqNrgolDDWN6Ssx1nFg6JDJQuaBFo4SL2i+MBoOQ16n2Pq1iBF5lH1PKnfCIOfqAGkmzPvdB9g==",
-      "license": "Apache-2.0",
+      "version": "4.25.0",
+      "resolved": "https://registry.npmjs.org/openai/-/openai-4.25.0.tgz",
+      "integrity": "sha512-qLMFOizjxKuDfQkBrczZPYo6XVL4bdcuz9MR11Q+M91kGcs8dQw+O90nRcC+qWuhaGphQkfXQJMn4cd7Yew3Kg==",
       "dependencies": {
         "@types/node": "^18.11.18",
         "@types/node-fetch": "^2.6.4",
         "abort-controller": "^3.0.0",
         "agentkeepalive": "^4.2.1",
+        "digest-fetch": "^1.3.0",
         "form-data-encoder": "1.7.2",
         "formdata-node": "^4.3.2",
-        "node-fetch": "^2.6.7"
+        "node-fetch": "^2.6.7",
+        "web-streams-polyfill": "^3.2.1"
       },
       "bin": {
         "openai": "bin/cli"
@@ -7121,6 +7167,14 @@
         "uuid": "dist/bin/uuid"
       }
     },
+    "node_modules/web-streams-polyfill": {
+      "version": "3.2.1",
+      "resolved": "https://registry.npmjs.org/web-streams-polyfill/-/web-streams-polyfill-3.2.1.tgz",
+      "integrity": "sha512-e0MO3wdXWKrLbL0DgGnUV7WHVuw9OUvL4hjgnPkIeEvESk74gAITi5G606JtZPp39cd8HA9VQzCIvA49LpPN5Q==",
+      "engines": {
+        "node": ">= 8"
+      }
+    },
     "node_modules/webidl-conversions": {
       "version": "3.0.1",
       "resolved": "https://registry.npmjs.org/webidl-conversions/-/webidl-conversions-3.0.1.tgz",
@@ -9340,6 +9394,11 @@
       "integrity": "sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw==",
       "dev": true
     },
+    "base-64": {
+      "version": "0.1.0",
+      "resolved": "https://registry.npmjs.org/base-64/-/base-64-0.1.0.tgz",
+      "integrity": "sha512-Y5gU45svrR5tI2Vt/X9GPd3L0HNIKzGu202EjxrXMpuc2V2CiKgemAbUUsqYmZJvPtCXoUKjNZwBJzsNScUbXA=="
+    },
     "base64-js": {
       "version": "1.5.1",
       "resolved": "https://registry.npmjs.org/base64-js/-/base64-js-1.5.1.tgz",
@@ -9479,6 +9538,11 @@
         "supports-color": "^7.1.0"
       }
     },
+    "charenc": {
+      "version": "0.0.2",
+      "resolved": "https://registry.npmjs.org/charenc/-/charenc-0.0.2.tgz",
+      "integrity": "sha512-yrLQ/yVUFXkzg7EDQsPieE/53+0RlaWTs+wBrvW36cyilJ2SaDWfl4Yj7MtLTXleV9uEKefbAGUPv2/iWSooRA=="
+    },
     "clean-stack": {
       "version": "2.2.0",
       "resolved": "https://registry.npmjs.org/clean-stack/-/clean-stack-2.2.0.tgz",
@@ -9559,6 +9623,11 @@
         "which": "^2.0.1"
       }
     },
+    "crypt": {
+      "version": "0.0.2",
+      "resolved": "https://registry.npmjs.org/crypt/-/crypt-0.0.2.tgz",
+      "integrity": "sha512-mCxBlsHFYh9C+HVpiEacem8FEBnMXgU9gy4zmNC+SXAZNB/1idgp/aulFJ4FgCi7GPEVbfyng092GqL2k2rmow=="
+    },
     "d": {
       "version": "1.0.1",
       "resolved": "https://registry.npmjs.org/d/-/d-1.0.1.tgz",
@@ -9666,6 +9735,15 @@
       "resolved": "https://registry.npmjs.org/diff-sequences/-/diff-sequences-26.6.2.tgz",
       "integrity": "sha512-Mv/TDa3nZ9sbc5soK+OoA74BsS3mL37yixCvUAQkiuA4Wz6YtwP/K47n2rv2ovzHZvoiQeA5FTQOschKkEwB0Q=="
     },
+    "digest-fetch": {
+      "version": "1.3.0",
+      "resolved": "https://registry.npmjs.org/digest-fetch/-/digest-fetch-1.3.0.tgz",
+      "integrity": "sha512-CGJuv6iKNM7QyZlM2T3sPAdZWd/p9zQiRNS9G+9COUCwzWFTs0Xp8NF5iePx7wtvhDykReiRRrSeNb4oMmB8lA==",
+      "requires": {
+        "base-64": "^0.1.0",
+        "md5": "^2.3.0"
+      }
+    },
     "dotenv": {
       "version": "6.2.0",
       "resolved": "https://registry.npmjs.org/dotenv/-/dotenv-6.2.0.tgz",
@@ -10728,6 +10806,11 @@
         "has-tostringtag": "^1.0.0"
       }
     },
+    "is-buffer": {
+      "version": "1.1.6",
+      "resolved": "https://registry.npmjs.org/is-buffer/-/is-buffer-1.1.6.tgz",
+      "integrity": "sha512-NcdALwpXkTm5Zvvbk7owOUSvVvBKDgKP5/ewfXEznmQFfs4ZRmanOeKBTjRVjka3QFoN6XJ+9F3USqfHqTaU5w=="
+    },
     "is-callable": {
       "version": "1.2.7",
       "resolved": "https://registry.npmjs.org/is-callable/-/is-callable-1.2.7.tgz",
@@ -11288,6 +11371,16 @@
         }
       }
     },
+    "md5": {
+      "version": "2.3.0",
+      "resolved": "https://registry.npmjs.org/md5/-/md5-2.3.0.tgz",
+      "integrity": "sha512-T1GITYmFaKuO91vxyoQMFETst+O71VUPEU3ze5GNzDm0OWdP8v1ziTaAEPUr/3kLsY3Sftgz242A1SetQiDL7g==",
+      "requires": {
+        "charenc": "0.0.2",
+        "crypt": "0.0.2",
+        "is-buffer": "~1.1.6"
+      }
+    },
     "micromatch": {
       "version": "4.0.5",
       "resolved": "https://registry.npmjs.org/micromatch/-/micromatch-4.0.5.tgz",
@@ -11621,17 +11714,19 @@
       }
     },
     "openai": {
-      "version": "4.53.2",
-      "resolved": "https://registry.npmjs.org/openai/-/openai-4.53.2.tgz",
-      "integrity": "sha512-ohYEv6OV3jsFGqNrgolDDWN6Ssx1nFg6JDJQuaBFo4SL2i+MBoOQ16n2Pq1iBF5lH1PKnfCIOfqAGkmzPvdB9g==",
+      "version": "4.25.0",
+      "resolved": "https://registry.npmjs.org/openai/-/openai-4.25.0.tgz",
+      "integrity": "sha512-qLMFOizjxKuDfQkBrczZPYo6XVL4bdcuz9MR11Q+M91kGcs8dQw+O90nRcC+qWuhaGphQkfXQJMn4cd7Yew3Kg==",
       "requires": {
         "@types/node": "^18.11.18",
         "@types/node-fetch": "^2.6.4",
         "abort-controller": "^3.0.0",
         "agentkeepalive": "^4.2.1",
+        "digest-fetch": "^1.3.0",
         "form-data-encoder": "1.7.2",
         "formdata-node": "^4.3.2",
-        "node-fetch": "^2.6.7"
+        "node-fetch": "^2.6.7",
+        "web-streams-polyfill": "^3.2.1"
       },
       "dependencies": {
         "@types/node": {
@@ -12650,6 +12745,11 @@
       "integrity": "sha512-+NYs2QeMWy+GWFOEm9xnn6HCDp0l7QBD7ml8zLUmJ+93Q5NF0NocErnwkTkXVFNiX3/fpC6afS8Dhb/gz7R7eg==",
       "dev": true
     },
+    "web-streams-polyfill": {
+      "version": "3.2.1",
+      "resolved": "https://registry.npmjs.org/web-streams-polyfill/-/web-streams-polyfill-3.2.1.tgz",
+      "integrity": "sha512-e0MO3wdXWKrLbL0DgGnUV7WHVuw9OUvL4hjgnPkIeEvESk74gAITi5G606JtZPp39cd8HA9VQzCIvA49LpPN5Q=="
+    },
     "webidl-conversions": {
       "version": "3.0.1",
       "resolved": "https://registry.npmjs.org/webidl-conversions/-/webidl-conversions-3.0.1.tgz",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jambonz/speech-utils",
-  "version": "0.1.15",
+  "version": "0.1.19",
   "description": "TTS-related speech utilities for jambonz",
   "main": "index.js",
   "author": "Dave Horton",
@@ -37,7 +37,7 @@
     "google-protobuf": "^3.21.2",
     "ibm-watson": "^8.0.0",
     "microsoft-cognitiveservices-speech-sdk": "1.38.0",
-    "openai": "^4.53.2",
+    "openai": "^4.25.0",
     "undici": "^6.4.0"
   },
   "devDependencies": {

test/synth.js

@@ -574,9 +574,9 @@ test('Elevenlabs speech synth tests', async(t) => {
     t.end(err);
   }
   client.quit();
-})
+});
 
-test('PlayHT speech synth tests', async(t) => {
+const testPlayHT = async(t, voice_engine) => {
   const fn = require('..');
   const {synthAudio, client} = fn(opts, logger);
 
@@ -584,26 +584,26 @@ test('PlayHT speech synth tests', async(t) => {
     t.pass('skipping PlayHT speech synth tests since PLAYHT_API_KEY or PLAYHT_USER_ID is/are not provided');
     return t.end();
   }
-  const text = 'Hi there and welcome to jambones!';
+  const text = 'Hi there and welcome to jambones! ' + Date.now();
   try {
-    let opts = await synthAudio(stats, {
+    const opts = await synthAudio(stats, {
       vendor: 'playht',
       credentials: {
         api_key: process.env.PLAYHT_API_KEY,
         user_id: process.env.PLAYHT_USER_ID,
-        voice_engine: 'PlayHT2.0-turbo',
+        voice_engine,
         options: JSON.stringify({
-          quality: "medium",
+          quality: 'medium',
           speed: 1,
           seed: 1,
           temperature: 1,
-          emotion: "female_happy",
+          emotion: 'female_happy',
           voice_guidance: 3,
           style_guidance: 20,
           text_guidance: 1,
         })
       },
-      language: 'en-US',
+      language: 'english',
       voice: 's3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json',
       text,
       renderForCaching: true
@@ -615,6 +615,14 @@ test('PlayHT speech synth tests', async(t) => {
     t.end(err);
   }
   client.quit();
+};
+
+test('PlayHT speech synth tests', async(t) => {
+  await testPlayHT(t, 'PlayHT2.0-turbo');
+});
+
+test('PlayHT3.0 speech synth tests', async(t) => {
+  await testPlayHT(t, 'Play3.0');
 });
 
 test('rimelabs speech synth tests', async(t) => {