@jambonz/speech-utils 0.1.16 → 0.1.18

package/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 = '';
@@ -769,6 +798,7 @@ const synthPlayHT = async(logger, {
     params += ',vendor=playht';
     params += `,voice=${voice}`;
     params += `,voice_engine=${voice_engine}`;
+    params += `,synthesize_url=${synthesizeUrl}`;
     params += ',write_cache_file=1';
     if (opts.quality) params += `,quality=${opts.quality}`;
     if (opts.speed) params += `,speed=${opts.speed}`;
@@ -778,6 +808,8 @@ const synthPlayHT = async(logger, {
     if (opts.voice_guidance) params += `,voice_guidance=${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 +820,18 @@ 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',

package/lib/utils.js

@@ -98,6 +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);
@@ -171,6 +176,7 @@ module.exports = {
   makeSynthKey,
   makeNuanceKey,
   makeIbmKey,
+  makePlayhtKey,
   makeAwsKey,
   makeVerbioKey,
   getNuanceAccessToken,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jambonz/speech-utils",
-  "version": "0.1.16",
+  "version": "0.1.18",
   "description": "TTS-related speech utilities for jambonz",
   "main": "index.js",
   "author": "Dave Horton",

package/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) => {