@jambonz/speech-utils 0.2.11 → 0.2.13

package/lib/synth-audio.js

@@ -98,7 +98,7 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
   logger = logger || noopLogger;
 
   assert.ok(['google', 'aws', 'polly', 'microsoft', 'wellsaid', 'nuance', 'nvidia', 'ibm', 'elevenlabs',
-    'whisper', 'deepgram', 'playht', 'rimelabs', 'verbio', 'cartesia'].includes(vendor) ||
+    'whisper', 'deepgram', 'playht', 'rimelabs', 'verbio', 'cartesia', 'inworld'].includes(vendor) ||
   vendor.startsWith('custom'),
   `synthAudio supported vendors are google, aws, microsoft, nuance, nvidia and wellsaid ..etc, not ${vendor}`);
   if ('google' === vendor) {
@@ -141,6 +141,10 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
     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 ('inworld' === vendor) {
+    assert.ok(voice, 'synthAudio requires voice when inworld is used');
+    assert.ok(credentials.api_key, 'synthAudio requires api_key when inworld is used');
+    assert.ok(credentials.model_id, 'synthAudio requires model_id when inworld is used');
   } else if ('rimelabs' === vendor) {
     assert.ok(voice, 'synthAudio requires voice when rimelabs is used');
     assert.ok(credentials.api_key, 'synthAudio requires api_key when rimelabs is used');
@@ -238,6 +242,10 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
         audioData = await synthCartesia(logger, {
           credentials, options, stats, language, voice, text, renderForCaching, disableTtsStreaming});
         break;
+      case 'inworld':
+        audioData = await synthInworld(logger, {
+          credentials, options, stats, language, voice, text, renderForCaching, disableTtsStreaming});
+        break;
       case 'rimelabs':
         audioData = await synthRimelabs(logger, {
           credentials, options, stats, language, voice, text, renderForCaching, disableTtsStreaming});
@@ -479,10 +487,10 @@ async function _synthOnPremMicrosoft(logger, {
     /* microsoft enforces some properties and uses voice xml element so if the user did not supply do it for them */
     const words = content.slice(7, -8).trim().replace(/(\r\n|\n|\r)/gm, ' ');
     // eslint-disable-next-line max-len
-    content = `<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="https://www.w3.org/2001/mstts" xml:lang="${language}"><lang xml:lang="${language}"><voice name="${voice}">${words}</voice></lang></speak>`;
+    content = `<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="https://www.w3.org/2001/mstts" xml:lang="${language}"><voice name="${voice}">${words}</voice></speak>`;
     logger.info({content}, 'synthMicrosoft');
   }
-  else if (JAMBONES_AZURE_ENABLE_SSML) {
+  else if (JAMBONES_AZURE_ENABLE_SSML && !content.startsWith('<speak')) {
     // eslint-disable-next-line max-len
     content = `<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="https://www.w3.org/2001/mstts" xml:lang="${language}"><voice name="${voice}"><lang xml:lang="${language}">${text}</lang></voice></speak>`;
   }
@@ -532,10 +540,10 @@ const synthMicrosoft = async(logger, {
     /* microsoft enforces some properties and uses voice xml element so if the user did not supply do it for them */
       const words = content.slice(7, -8).trim().replace(/(\r\n|\n|\r)/gm, ' ');
       // eslint-disable-next-line max-len
-      content = `<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="https://www.w3.org/2001/mstts" xml:lang="${language}"><lang xml:lang="${language}"><voice name="${voice}">${words}</voice></lang></speak>`;
+      content = `<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="https://www.w3.org/2001/mstts" xml:lang="${language}"><voice name="${voice}">${words}</voice></speak>`;
       logger.info({content}, 'synthMicrosoft');
     }
-    else if (JAMBONES_AZURE_ENABLE_SSML) {
+    else if (JAMBONES_AZURE_ENABLE_SSML && !content.startsWith('<speak')) {
       // eslint-disable-next-line max-len
       content = `<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="https://www.w3.org/2001/mstts" xml:lang="${language}"><voice name="${voice}"><lang xml:lang="${language}">${text}</lang></voice></speak>`;
     }
@@ -954,6 +962,70 @@ const synthPlayHT = async(client, logger, {
   }
 };
 
+const synthInworld = async(logger, {
+  credentials, options, stats, voice, text, renderForCaching, disableTtsStreaming
+}) => {
+  const {api_key, model_id, 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 (!JAMBONES_DISABLE_TTS_STREAMING && !renderForCaching && !disableTtsStreaming) {
+    let params = '';
+    params += `{api_key=${api_key}`;
+    params += `,model_id=${model_id}`;
+    params += ',vendor=inworld';
+    params += `,voice=${voice}`;
+    params += ',write_cache_file=1';
+    if (opts.temperature) params += `,temperature=${opts.temperature}`;
+    if (opts.audioConfig?.pitch) params += `,pitch=${opts.pitch}`;
+    if (opts.audioConfig?.speakingRate) params += `,speakingRate=${opts.speakingRate}`;
+    params += '}';
+
+    return {
+      filePath: `say:${params}${text.replace(/\n/g, ' ').replace(/\r/g, ' ')}`,
+      servedFromCache: false,
+      rtt: 0
+    };
+  }
+
+  try {
+    const url = 'https://api.inworld.ai/tts/v1/voice';
+    const sampleRate = 8000;
+    const options = {
+      method: 'POST',
+      headers: {
+        'Authorization': `Basic ${api_key}`,
+        'Content-Type': 'application/json'
+      },
+      body: JSON.stringify({
+        text,
+        voiceId: voice,
+        modelId: model_id,
+        audioConfig: {
+          ...(opts.audioConfig || {}),
+          audioEncoding: 'MP3',
+        }
+      })
+    };
+
+    const response = await fetch(url, options);
+
+    if (!response.ok) {
+      throw new Error(await response.text());
+    }
+    const json = await response.json();
+    return {
+      audioContent: Buffer.from(json.audioContent, 'base64'),
+      extension: 'mp3',
+      sampleRate
+    };
+  } catch (err) {
+    logger.info({err}, 'synth inworld returned error');
+    stats.increment('tts.count', ['vendor:inworld', 'accepted:no']);
+    throw err;
+  }
+};
+
 const synthRimelabs = async(logger, {
   credentials, options, stats, language, voice, text, renderForCaching, disableTtsStreaming
 }) => {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jambonz/speech-utils",
-  "version": "0.2.11",
+  "version": "0.2.13",
   "description": "TTS-related speech utilities for jambonz",
   "main": "index.js",
   "author": "Dave Horton",

package/test/synth.js

@@ -720,6 +720,36 @@ test('Cartesia speech synth tests', async(t) => {
   client.quit();
 });
 
+test('inworld speech synth', async(t) => {
+  const fn = require('..');
+  const {synthAudio, client} = fn(opts, logger);
+
+  if (!process.env.INWORLD_API_KEY) {
+    t.pass('skipping inworld speech synth tests since INWORLD_API_KEY is not provided');
+    return t.end();
+  }
+  const text = 'Hi there and welcome to jambones!';
+  try {
+    const opts = await synthAudio(stats, {
+      vendor: 'inworld',
+      credentials: {
+        api_key: process.env.INWORLD_API_KEY,
+        model_id: 'inworld-tts-1'
+      },
+      language: 'en',
+      voice: 'Ashley',
+      text,
+      renderForCaching: true
+    });
+    t.ok(!opts.servedFromCache, `successfully synthesized inworld audio to ${opts.filePath}`);
+
+  } catch (err) {
+    console.error(JSON.stringify(err));
+    t.end(err);
+  }
+  client.quit();
+});
+
 test('rimelabs speech synth tests mist', async(t) => {
   const fn = require('..');
   const {synthAudio, client} = fn(opts, logger);