support mod_playht_tts

lib/synth-audio.js

@@ -85,7 +85,7 @@ async function synthAudio(client, logger, stats, { account_sid,
   logger = logger || noopLogger;
 
   assert.ok(['google', 'aws', 'polly', 'microsoft',
-    'wellsaid', 'nuance', 'nvidia', 'ibm', 'elevenlabs', 'whisper', 'deepgram'].includes(vendor) ||
+    'wellsaid', 'nuance', 'nvidia', 'ibm', 'elevenlabs', 'whisper', 'deepgram', 'playht'].includes(vendor) ||
   vendor.startsWith('custom'),
   `synthAudio supported vendors are google, aws, microsoft, nuance, nvidia and wellsaid, not ${vendor}`);
   if ('google' === vendor) {
@@ -123,6 +123,11 @@ async function synthAudio(client, logger, stats, { account_sid,
     assert.ok(voice, 'synthAudio requires voice when elevenlabs is used');
     assert.ok(credentials.api_key, 'synthAudio requires api_key when elevenlabs is used');
     assert.ok(credentials.model_id, 'synthAudio requires model_id when elevenlabs is used');
+  }  else if ('playht' === vendor) {
+    assert.ok(voice, 'synthAudio requires voice when playht is used');
+    assert.ok(credentials.api_key, 'synthAudio requires api_key when playht is used');
+    assert.ok(credentials.user_id, 'synthAudio requires user_id when playht is used');
+    assert.ok(credentials.voice_engine, 'synthAudio requires voice_engine when playht is used');
   } else if ('whisper' === vendor) {
     assert.ok(voice, 'synthAudio requires voice when whisper is used');
     assert.ok(credentials.model_id, 'synthAudio requires model when whisper is used');
@@ -206,6 +211,12 @@ async function synthAudio(client, logger, stats, { account_sid,
         });
         if (audioBuffer?.filePath) return audioBuffer;
         break;
+      case 'playht':
+        audioBuffer = await synthPlayHT(logger, {
+          credentials, options, stats, language, voice, text, renderForCaching, disableTtsStreaming, filePath
+        });
+        if (audioBuffer?.filePath) return audioBuffer;
+        break;
       case 'whisper':
         audioBuffer = await synthWhisper(logger, {
           credentials, stats, voice, text, renderForCaching, disableTtsStreaming});
@@ -682,6 +693,61 @@ const synthElevenlabs = async(logger, {
   }
 };
 
+const synthPlayHT = async(logger, {
+  credentials, options, stats, voice, 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 || '{}');
+
+  /* default to using the streaming interface, unless disabled by env var OR we want just a cache file */
+  if (!process.env.JAMBONES_DISABLE_TTS_STREAMING && !renderForCaching && !disableTtsStreaming) {
+    let params = '';
+    params += `{api_key=${api_key}`;
+    params += `,user_id=${user_id}`;
+    params += ',vendor=playht';
+    params += `,voice=${voice}`;
+    params += `,voice_engine=${voice_engine}`;
+    params += ',write_cache_file=1';
+    if (opts.quality) params += `,quality=${opts.quality}`;
+    if (opts.speed) params += `,speed=${opts.speed}`;
+    if (opts.seed) params += `,style=${opts.seed}`;
+    if (opts.temperature) params += `,temperature=${opts.temperature}`;
+    if (opts.emotion) params += `,emotion=${opts.emotion}`;
+    if (opts.voice_guidance) params += `,voice_guidance=${opts.voice_guidance}`;
+    if (opts.style_guidance) params += `,style_guidance=${opts.style_guidance}`;
+    if (opts.text_guidance) params += `,text_guidance=${opts.text_guidance}`;
+    params += '}';
+
+    return {
+      filePath: `say:${params}${text.replace(/\n/g, ' ').replace(/\r/g, ' ')}`,
+      servedFromCache: false,
+      rtt: 0
+    };
+  }
+
+  try {
+    const post = bent('https://api.play.ht', 'POST', 'buffer', {
+      'AUTHORIZATION': api_key,
+      'X-USER-ID': user_id,
+      'Accept': 'audio/mpeg',
+      'Content-Type': 'application/json'
+    });
+    const mp3 = await post('/api/v2/tts/stream', {
+      text,
+      voice,
+      voice_engine,
+      output_format: 'mp3',
+      sample_rate: 8000,
+      ...opts
+    });
+    return mp3;
+  } catch (err) {
+    logger.info({err}, 'synth PlayHT returned error');
+    stats.increment('tts.count', ['vendor:playht', 'accepted:no']);
+    throw err;
+  }
+};
+
 const synthWhisper = async(logger, {credentials, stats, voice, text, renderForCaching, disableTtsStreaming}) => {
   const {api_key, model_id, baseURL, timeout, speed} = credentials;
   /* if the env is set to stream then bag out, unless we are specifically rendering to generate a cache file */

test/synth.js

@@ -549,6 +549,47 @@ test('Elevenlabs speech synth tests', async(t) => {
   client.quit();
 })
 
+test('PlayHT speech synth tests', async(t) => {
+  const fn = require('..');
+  const {synthAudio, client} = fn(opts, logger);
+
+  if (!process.env.PLAYHT_API_KEY || !process.env.PLAYHT_USER_ID) {
+    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!';
+  try {
+    let 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',
+        options: JSON.stringify({
+          quality: "medium",
+          speed: 1,
+          seed: 1,
+          temperature: 1,
+          emotion: "female_happy",
+          voice_guidance: 3,
+          style_guidance: 20,
+          text_guidance: 1,
+        })
+      },
+      language: 'en-US',
+      voice: 's3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json',
+      text,
+      renderForCaching: true
+    });
+    t.ok(!opts.servedFromCache, `successfully synthesized eleven audio to ${opts.filePath}`);
+
+  } catch (err) {
+    console.error(JSON.stringify(err));
+    t.end(err);
+  }
+  client.quit();
+})
+
 test('whisper speech synth tests', async(t) => {
   const fn = require('..');
   const {synthAudio, client} = fn(opts, logger);