0.1.1

add verbio tts/stt

.github/workflows/ci.yml

@@ -8,8 +8,8 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
-      - uses: actions/setup-node@v3
+      - uses: actions/setup-node@v4
         with:
           node-version: lts/*
       - run: npm install
@@ -32,5 +32,7 @@ jobs:
           ELEVENLABS_API_KEY: ${{ secrets.ELEVENLABS_API_KEY }}
           ELEVENLABS_VOICE_ID: ${{ secrets.ELEVENLABS_VOICE_ID }}
           ELEVENLABS_MODEL_ID: ${{ secrets.ELEVENLABS_MODEL_ID }}
+          PLAYHT_USER_ID: ${{ secrets.PLAYHT_USER_ID }}
+          PLAYHT_API_KEY: ${{ secrets.PLAYHT_API_KEY }}
           JAMBONES_HTTP_PROXY_IP: 127.0.0.1
           JAMBONES_HTTP_PROXY_PORT: 3128

index.js

@@ -13,10 +13,11 @@ module.exports = (opts, logger) => {
     getTtsSize: require('./lib/get-tts-size').bind(null, client, logger),
     purgeTtsCache: require('./lib/purge-tts-cache').bind(null, client, logger),
     addFileToCache: require('./lib/add-file-to-cache').bind(null, client, logger),
-    synthAudio: require('./lib/synth-audio').bind(null, client, logger),
+    synthAudio: require('./lib/synth-audio').bind(null, client, createHash, retrieveHash, logger),
+    getVerbioAccessToken: require('./lib/get-verbio-token').bind(null, client, logger),
     getNuanceAccessToken: require('./lib/get-nuance-access-token').bind(null, client, logger),
     getIbmAccessToken: require('./lib/get-ibm-access-token').bind(null, client, logger),
     getAwsAuthToken: require('./lib/get-aws-sts-token').bind(null, logger, createHash, retrieveHash),
-    getTtsVoices: require('./lib/get-tts-voices').bind(null, client, logger),
+    getTtsVoices: require('./lib/get-tts-voices').bind(null, client, createHash, retrieveHash, logger),
   };
 };

lib/constants.js

@@ -0,0 +1,3 @@
+module.exports = {
+  HTTP_TIMEOUT: 5000
+};

lib/get-aws-sts-token.js

@@ -1,32 +1,41 @@
-const { STSClient, GetSessionTokenCommand } = require('@aws-sdk/client-sts');
+const { STSClient, GetSessionTokenCommand, AssumeRoleCommand } = require('@aws-sdk/client-sts');
 const {makeAwsKey, noopLogger} = require('./utils');
 const debug = require('debug')('jambonz:speech-utils');
 const EXPIRY = 3600;
 
 async function getAwsAuthToken(
-  logger,
+  logger, createHash, retrieveHash,
-  createHash, retrieveHash,
+  awsAccessKeyId, awsSecretAccessKey, awsRegion, roleArn = null) {
-  awsAccessKeyId, awsSecretAccessKey, awsRegion) {
   logger = logger || noopLogger;
   try {
-    const key = makeAwsKey(awsAccessKeyId);
+    const key = makeAwsKey(roleArn || awsAccessKeyId);
     const obj = await retrieveHash(key);
     if (obj) return {...obj, servedFromCache: true};
 
-    /* access token not found in cache, so generate it using STS */
+    let data;
-    const stsClient = new STSClient({
+    if (roleArn) {
-      region: awsRegion,
+      const stsClient = new STSClient({ region: awsRegion});
-      credentials: {
+      const roleToAssume = { RoleArn: roleArn, RoleSessionName: 'Jambonz_Speech', DurationSeconds: EXPIRY};
-        accessKeyId: awsAccessKeyId,
+      const command = new AssumeRoleCommand(roleToAssume);
-        secretAccessKey: awsSecretAccessKey,
+
-      }
+      data = await stsClient.send(command);
-    });
+    } else {
-    const command = new GetSessionTokenCommand({DurationSeconds: EXPIRY});
+      /* access token not found in cache, so generate it using STS */
-    const data = await stsClient.send(command);
+      const stsClient = new STSClient({
+        region: awsRegion,
+        credentials: {
+          accessKeyId: awsAccessKeyId,
+          secretAccessKey: awsSecretAccessKey,
+        }
+      });
+      const command = new GetSessionTokenCommand({DurationSeconds: EXPIRY});
+      data = await stsClient.send(command);
+    }
 
     const credentials = {
       accessKeyId: data.Credentials.AccessKeyId,
       secretAccessKey: data.Credentials.SecretAccessKey,
+      sessionToken: data.Credentials.SessionToken,
       securityToken: data.Credentials.SessionToken
     };
 

lib/get-ibm-access-token.js

@@ -2,8 +2,8 @@ const formurlencoded = require('form-urlencoded');
 const {Pool} = require('undici');
 const pool = new Pool('https://iam.cloud.ibm.com');
 const {makeIbmKey, noopLogger} = require('./utils');
+const { HTTP_TIMEOUT } = require('./constants');
 const debug = require('debug')('jambonz:realtimedb-helpers');
-const HTTP_TIMEOUT = 5000;
 
 async function getIbmAccessToken(client, logger, apiKey) {
   logger = logger || noopLogger;

lib/get-nuance-access-token.js

@@ -2,8 +2,8 @@ const formurlencoded = require('form-urlencoded');
 const {Pool} = require('undici');
 const pool = new Pool('https://auth.crt.nuance.com');
 const {makeNuanceKey, makeBasicAuthHeader, noopLogger} = require('./utils');
+const { HTTP_TIMEOUT } = require('./constants');
 const debug = require('debug')('jambonz:realtimedb-helpers');
-const HTTP_TIMEOUT = 5000;
 
 async function getNuanceAccessToken(client, logger, clientId, secret, scope) {
   logger = logger || noopLogger;

lib/get-tts-voices.js

@@ -1,11 +1,16 @@
 const assert = require('assert');
 const {noopLogger, createNuanceClient, createKryptonClient} = require('./utils');
 const getNuanceAccessToken = require('./get-nuance-access-token');
+const getVerbioAccessToken = require('./get-verbio-token');
 const {GetVoicesRequest, Voice} = require('../stubs/nuance/synthesizer_pb');
 const TextToSpeechV1 = require('ibm-watson/text-to-speech/v1');
 const { IamAuthenticator } = require('ibm-watson/auth');
 const ttsGoogle = require('@google-cloud/text-to-speech');
 const { PollyClient, DescribeVoicesCommand } = require('@aws-sdk/client-polly');
+const getAwsAuthToken = require('./get-aws-sts-token');
+const {Pool} = require('undici');
+const { HTTP_TIMEOUT } = require('./constants');
+const verbioVoicePool = new Pool('https://us.rest.speechcenter.verbio.com');
 
 const getIbmVoices = async(client, logger, credentials) => {
   const {tts_region, tts_api_key} = credentials;
@@ -87,16 +92,26 @@ const getGoogleVoices = async(_client, logger, credentials) => {
   return await client.listVoices();
 };
 
-const getAwsVoices = async(_client, logger, credentials) => {
+const getAwsVoices = async(_client, createHash, retrieveHash, logger, credentials) => {
   try {
-    const {region, accessKeyId, secretAccessKey} = credentials;
+    const {region, accessKeyId, secretAccessKey, roleArn} = credentials;
-    const client = new PollyClient({
+    let client = null;
-      region,
+    if (accessKeyId && secretAccessKey) {
-      credentials: {
+      client = new PollyClient({
-        accessKeyId,
+        region,
-        secretAccessKey
+        credentials: {
-      }
+          accessKeyId,
-    });
+          secretAccessKey
+        }
+      });
+    } else if (roleArn) {
+      client = new PollyClient({
+        region,
+        credentials: await getAwsAuthToken(logger, createHash, retrieveHash, null, null, region, roleArn),
+      });
+    } else {
+      client = new PollyClient({region});
+    }
     const command = new DescribeVoicesCommand({});
     const response = await client.send(command);
     return response;
@@ -106,6 +121,26 @@ const getAwsVoices = async(_client, logger, credentials) => {
   }
 };
 
+const getVerbioVoices = async(client, logger, credentials) => {
+  try {
+    const access_token = await getVerbioAccessToken(client, logger, credentials);
+    const { body} =  await verbioVoicePool.request({
+      path: '/api/v1/voices',
+      method: 'GET',
+      headers: {
+        'Authorization': `Bearer ${access_token.access_token}`,
+        'User-Agent': 'jambonz'
+      },
+      timeout: HTTP_TIMEOUT,
+      followRedirects: false
+    });
+    return await body.json();
+  } catch (err) {
+    logger.info({err}, 'getVerbioVoices - failed to list voices for Verbio');
+    throw err;
+  }
+};
+
 /**
  * Synthesize speech to an mp3 file, and also cache the generated speech
  * in redis (base64 format) for 24 hours so as to avoid unnecessarily paying
@@ -122,10 +157,10 @@ const getAwsVoices = async(_client, logger, credentials) => {
  * @returns object containing filepath to an mp3 file in the /tmp folder containing
  * the synthesized audio, and a variable indicating whether it was served from cache
  */
-async function getTtsVoices(client, logger, {vendor, credentials}) {
+async function getTtsVoices(client, createHash, retrieveHash, logger, {vendor, credentials}) {
   logger = logger || noopLogger;
 
-  assert.ok(['nuance', 'ibm', 'google', 'aws', 'polly'].includes(vendor),
+  assert.ok(['nuance', 'ibm', 'google', 'aws', 'polly', 'verbio'].includes(vendor),
     `getTtsVoices not supported for vendor ${vendor}`);
 
   switch (vendor) {
@@ -137,7 +172,9 @@ async function getTtsVoices(client, logger, {vendor, credentials}) {
       return getGoogleVoices(client, logger, credentials);
     case 'aws':
     case 'polly':
-      return getAwsVoices(client, logger, credentials);
+      return getAwsVoices(client, createHash, retrieveHash, logger, credentials);
+    case 'verbio':
+      return getVerbioVoices(client, logger, credentials);
     default:
       break;
   }

lib/get-verbio-token.js

@@ -0,0 +1,51 @@
+const {Pool} = require('undici');
+const { noopLogger, makeVerbioKey } = require('./utils');
+const { HTTP_TIMEOUT } = require('./constants');
+const pool = new Pool('https://auth.speechcenter.verbio.com:444');
+const debug = require('debug')('jambonz:realtimedb-helpers');
+
+async function getVerbioAccessToken(client, logger, credentials) {
+  logger = logger || noopLogger;
+  const { client_id, client_secret } = credentials;
+  try {
+    const key = makeVerbioKey(client_id);
+    const access_token = await client.get(key);
+    if (access_token) {
+      return {access_token, servedFromCache: true};
+    }
+
+    const payload = {
+      client_id,
+      client_secret
+    };
+
+    const {statusCode, headers, body} =  await pool.request({
+      path: '/api/v1/token',
+      method: 'POST',
+      headers: {
+        'Content-Type': 'application/json',
+        'User-Agent': 'jambonz'
+      },
+      body: JSON.stringify(payload),
+      timeout: HTTP_TIMEOUT,
+      followRedirects: false
+    });
+
+    if (200 !== statusCode) {
+      logger.debug({statusCode, headers, body: await body.text()}, 'error fetching access token from Verbio');
+      const err = new Error();
+      err.statusCode = statusCode;
+      throw err;
+    }
+    const json = await body.json();
+    const expiry =  Math.floor(json.expiration_time - Date.now() / 1000 - 30);
+    await client.set(key, json.access_token, 'EX', expiry);
+    return {...json, servedFromCache: false};
+  } catch (err) {
+    debug(err, `getVerbioAccessToken: Error retrieving Verbio access token for client_id ${client_id}`);
+    logger.error(err, `getVerbioAccessToken: Error retrieving Verbio access token for client_id ${client_id}`);
+    throw err;
+  }
+}
+
+module.exports = getVerbioAccessToken;

lib/synth-audio.js

@@ -22,6 +22,7 @@ const {
   noopLogger
 } = require('./utils');
 const getNuanceAccessToken = require('./get-nuance-access-token');
+const getVerbioAccessToken = require('./get-verbio-token');
 const {
   SynthesisRequest,
   Voice,
@@ -39,6 +40,7 @@ const debug = require('debug')('jambonz:realtimedb-helpers');
 const EXPIRES = (process.env.JAMBONES_TTS_CACHE_DURATION_MINS || 4 * 60) * 60; // cache tts for 4 hours
 const TMP_FOLDER = '/tmp';
 const OpenAI = require('openai');
+const getAwsAuthToken = require('./get-aws-sts-token');
 
 
 const trimTrailingSilence = (buffer) => {
@@ -75,19 +77,19 @@ const trimTrailingSilence = (buffer) => {
  * @returns object containing filepath to an mp3 file in the /tmp folder containing
  * the synthesized audio, and a variable indicating whether it was served from cache
  */
-async function synthAudio(client, logger, stats, { account_sid,
+async function synthAudio(client, createHash, retrieveHash, logger, stats, { account_sid,
   vendor, language, voice, gender, text, engine, salt, model, credentials, deploymentId,
-  disableTtsCache, renderForCaching, options
+  disableTtsCache, renderForCaching, disableTtsStreaming, options
 }) {
   let audioBuffer;
   let servedFromCache = false;
   let rtt;
   logger = logger || noopLogger;
 
-  assert.ok(['google', 'aws', 'polly', 'microsoft',
+  assert.ok(['google', 'aws', 'polly', 'microsoft', 'wellsaid', 'nuance', 'nvidia', 'ibm', 'elevenlabs',
-    'wellsaid', 'nuance', 'nvidia', 'ibm', 'elevenlabs', 'whisper', 'deepgram'].includes(vendor) ||
+    'whisper', 'deepgram', 'playht', 'rimelabs', 'verbio'].includes(vendor) ||
   vendor.startsWith('custom'),
-  `synthAudio supported vendors are google, aws, microsoft, nuance, nvidia and wellsaid, not ${vendor}`);
+  `synthAudio supported vendors are google, aws, microsoft, nuance, nvidia and wellsaid ..etc, not ${vendor}`);
   if ('google' === vendor) {
     assert.ok(language, 'synthAudio requires language when google is used');
   }
@@ -123,12 +125,25 @@ 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 ('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');
+    assert.ok(credentials.model_id, 'synthAudio requires model_id when rimelabs 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');
     assert.ok(credentials.api_key, 'synthAudio requires api_key when whisper is used');
   } else  if (vendor.startsWith('custom')) {
     assert.ok(credentials.custom_tts_url, `synthAudio requires custom_tts_url in credentials when ${vendor} is used`);
+  } else if ('verbio' === vendor) {
+    assert.ok(voice, 'synthAudio requires voice when verbio is used');
+    assert.ok(credentials.client_id, 'synthAudio requires client_id when verbio is used');
+    assert.ok(credentials.client_secret, 'synthAudio requires client_secret when verbio is used');
   }
   const key = makeSynthKey({
     account_sid,
@@ -139,14 +154,14 @@ async function synthAudio(client, logger, stats, { account_sid,
     text
   });
   let filePath;
-  if (['nuance', 'nvidia'].includes(vendor) ||
+  if (['nuance', 'nvidia', 'verbio'].includes(vendor) ||
     (
-      process.env.JAMBONES_TTS_TRIM_SILENCE &&
+      (process.env.JAMBONES_TTS_TRIM_SILENCE || !process.env.JAMBONES_DISABLE_TTS_STREAMING) &&
       ['microsoft', 'azure'].includes(vendor)
     ) ||
     (
       !process.env.JAMBONES_DISABLE_TTS_STREAMING &&
-      vendor === 'elevenlabs'
+      ['elevenlabs', 'deepgram', 'rimelabs'].includes(vendor)
     )
   ) {
     filePath = `${TMP_FOLDER}/${key.replace('tts:', `tts-${salt || ''}`)}.r8`;
@@ -178,12 +193,15 @@ async function synthAudio(client, logger, stats, { account_sid,
       case 'aws':
       case 'polly':
         vendorLabel = 'aws';
-        audioBuffer = await synthPolly(logger, {credentials, stats, language, voice, text, engine});
+        audioBuffer = await synthPolly(createHash, retrieveHash, logger,
+          {credentials, stats, language, voice, text, engine});
         break;
       case 'azure':
       case 'microsoft':
         vendorLabel = 'microsoft';
-        audioBuffer = await synthMicrosoft(logger, {credentials, stats, language, voice, text, deploymentId, filePath});
+        audioBuffer = await synthMicrosoft(logger, {credentials, stats, language, voice, text, deploymentId,
+          filePath, renderForCaching, disableTtsStreaming});
+        if (audioBuffer?.filePath) return audioBuffer;
         break;
       case 'nuance':
         model = model || 'enhanced';
@@ -200,24 +218,36 @@ async function synthAudio(client, logger, stats, { account_sid,
         break;
       case 'elevenlabs':
         audioBuffer = await synthElevenlabs(logger, {
-          credentials, options, stats, language, voice, text, renderForCaching, filePath
+          credentials, options, stats, language, voice, text, renderForCaching, disableTtsStreaming, filePath
         });
-        if (typeof audioBuffer === 'object' && audioBuffer.filePath) {
+        if (audioBuffer?.filePath) return audioBuffer;
-          return audioBuffer;
+        break;
-        }
+      case 'playht':
-        else {
+        audioBuffer = await synthPlayHT(logger, {
-          audioBuffer = await synthElevenlabs(logger, {credentials, options, stats, language, voice, text, filePath});
+          credentials, options, stats, language, voice, text, renderForCaching, disableTtsStreaming, filePath
-        }
+        });
+        if (audioBuffer?.filePath) return audioBuffer;
+        break;
+      case 'rimelabs':
+        audioBuffer = await synthRimelabs(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});
+        audioBuffer = await synthWhisper(logger, {
-        if (typeof audioBuffer === 'object' && audioBuffer.filePath) {
+          credentials, stats, voice, text, renderForCaching, disableTtsStreaming});
-          return audioBuffer;
+        if (audioBuffer?.filePath) return audioBuffer;
-        }
+        break;
-        audioBuffer = await synthWhisper(logger, {credentials, stats, voice, text});
+      case 'verbio':
+        audioBuffer = await synthVerbio(client, logger, {
+          credentials, stats, voice, text, renderForCaching, disableTtsStreaming});
+        if (audioBuffer?.filePath) return audioBuffer;
         break;
       case 'deepgram':
-        audioBuffer = await synthDeepgram(logger, {credentials, stats, model, text});
+        audioBuffer = await synthDeepgram(logger, {credentials, stats, model, text,
+          renderForCaching, disableTtsStreaming});
+        if (audioBuffer?.filePath) return audioBuffer;
         break;
       case vendor.startsWith('custom') ? vendor : 'cant_match_value':
         ({ audioBuffer, filePath } = await synthCustomVendor(logger,
@@ -245,16 +275,28 @@ async function synthAudio(client, logger, stats, { account_sid,
   });
 }
 
-const synthPolly = async(logger, {credentials, stats, language, voice, engine, text}) => {
+const synthPolly = async(createHash, retrieveHash, logger,
+  {credentials, stats, language, voice, engine, text}) => {
   try {
-    const {region, accessKeyId, secretAccessKey} = credentials;
+    const {region, accessKeyId, secretAccessKey, roleArn} = credentials;
-    const polly = new PollyClient({
+    let polly;
-      region,
+    if (accessKeyId && secretAccessKey) {
-      credentials: {
+      polly = new PollyClient({
-        accessKeyId,
+        region,
-        secretAccessKey
+        credentials: {
-      }
+          accessKeyId,
-    });
+          secretAccessKey
+        }
+      });
+    } else if (roleArn) {
+      polly = new PollyClient({
+        region,
+        credentials: await getAwsAuthToken(logger, createHash, retrieveHash, null, null, region, roleArn),
+      });
+    } else {
+      // AWS RoleArn assigned to Instance profile
+      polly = new PollyClient({region});
+    }
     const opts = {
       Engine: engine,
       OutputFormat: 'mp3',
@@ -348,7 +390,7 @@ async function _synthOnPremMicrosoft(logger, {
   text,
   filePath
 }) {
-  const {use_custom_tts, custom_tts_endpoint_url} = credentials;
+  const {use_custom_tts, custom_tts_endpoint_url, api_key} = credentials;
   let content = text;
 
   if (use_custom_tts && !content.startsWith('<speak')) {
@@ -372,7 +414,8 @@ async function _synthOnPremMicrosoft(logger, {
     const post = bent('POST', 'buffer', {
       'X-Microsoft-OutputFormat': trimSilence ? 'raw-8khz-16bit-mono-pcm' : 'audio-16khz-32kbitrate-mono-mp3',
       'Content-Type': 'application/ssml+xml',
-      'User-Agent': 'Jambonz'
+      'User-Agent': 'Jambonz',
+      ...(api_key && {'Ocp-Apim-Subscription-Key': api_key})
     });
     const mp3 = await post(custom_tts_endpoint_url, content);
     return mp3;
@@ -388,10 +431,48 @@ const synthMicrosoft = async(logger, {
   language,
   voice,
   text,
-  filePath
+  filePath,
+  renderForCaching,
+  disableTtsStreaming
 }) => {
   try {
     const {api_key: apiKey, region, use_custom_tts, custom_tts_endpoint, custom_tts_endpoint_url} = credentials;
+    // let clean up the text
+    let content = text;
+    if (use_custom_tts && !content.startsWith('<speak')) {
+      /**
+       * Note: it seems that to use custom voice ssml is required with the voice attribute
+       * Otherwise sending plain text we get "Voice does not match"
+       */
+      content = `<speak>${text}</speak>`;
+    }
+
+    if (content.startsWith('<speak>')) {
+      /* microsoft enforces some properties and uses voice xml element so if the user did not supply do it for them */
+      const words = content.slice(7, -8).trim().replace(/(\r\n|\n|\r)/gm, ' ');
+      // eslint-disable-next-line max-len
+      content = `<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="https://www.w3.org/2001/mstts" xml:lang="${language}"><voice name="${voice}">${words}</voice></speak>`;
+      logger.info({content}, 'synthMicrosoft');
+    }
+    if (!process.env.JAMBONES_DISABLE_TTS_STREAMING && !renderForCaching && !disableTtsStreaming) {
+      let params = '';
+      params += `{api_key=${apiKey}`;
+      params += `,language=${language}`;
+      params += ',vendor=microsoft';
+      params += `,voice=${voice}`;
+      params += ',write_cache_file=1';
+      if (region) params += `,region=${region}`;
+      if (custom_tts_endpoint) params += `,endpointId=${custom_tts_endpoint}`;
+      if (custom_tts_endpoint_url) params += `,endpoint=${custom_tts_endpoint_url}`;
+      if (process.env.JAMBONES_HTTP_PROXY_IP) params += `,http_proxy_ip=${process.env.JAMBONES_HTTP_PROXY_IP}`;
+      if (process.env.JAMBONES_HTTP_PROXY_PORT) params += `,http_proxy_port=${process.env.JAMBONES_HTTP_PROXY_PORT}`;
+      params += '}';
+      return {
+        filePath: `say:${params}${content.replace(/\n/g, ' ')}`,
+        servedFromCache: false,
+        rtt: 0
+      };
+    }
     if (use_custom_tts && custom_tts_endpoint_url) {
       return await _synthOnPremMicrosoft(logger, {
         credentials,
@@ -403,20 +484,12 @@ const synthMicrosoft = async(logger, {
       });
     }
     const trimSilence = filePath.endsWith('.r8');
-    let content = text;
     const speechConfig = SpeechConfig.fromSubscription(apiKey, region);
     speechConfig.speechSynthesisLanguage = language;
     speechConfig.speechSynthesisVoiceName = voice;
     if (use_custom_tts && custom_tts_endpoint) {
       speechConfig.endpointId = custom_tts_endpoint;
     }
-    if (use_custom_tts && !content.startsWith('<speak')) {
-      /**
-       * Note: it seems that to use custom voice ssml is required with the voice attribute
-       * Otherwise sending plain text we get "Voice does not match"
-       */
-      content = `<speak>${text}</speak>`;
-    }
     speechConfig.speechSynthesisOutputFormat = trimSilence ?
       SpeechSynthesisOutputFormat.Raw8Khz16BitMonoPcm :
       SpeechSynthesisOutputFormat.Audio16Khz32KBitRateMonoMp3;
@@ -428,14 +501,6 @@ const synthMicrosoft = async(logger, {
     }
     const synthesizer = new SpeechSynthesizer(speechConfig);
 
-    if (content.startsWith('<speak>')) {
-      /* 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="${language}"><voice name="${voice}">${words}</voice></speak>`;
-      logger.info({content}, 'synthMicrosoft');
-    }
-
     return new Promise((resolve, reject) => {
       const speakAsync = content.startsWith('<speak') ?
         synthesizer.speakSsmlAsync.bind(synthesizer) :
@@ -611,14 +676,18 @@ const synthCustomVendor = async(logger, {credentials, stats, language, voice, te
   }
 };
 
-const synthElevenlabs = async(logger, {credentials, options, stats, language, voice, text, renderForCaching}) => {
+const synthElevenlabs = 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 (!process.env.JAMBONES_DISABLE_TTS_STREAMING && !renderForCaching) {
+  if (!process.env.JAMBONES_DISABLE_TTS_STREAMING && !renderForCaching && !disableTtsStreaming) {
     let params = '';
     params += `{api_key=${api_key}`;
+    params += ',vendor=elevenlabs';
+    params += `,voice=${voice}`;
     params += `,model_id=${model_id}`;
     params += `,optimize_streaming_latency=${opts.optimize_streaming_latency || 2}`;
     params += ',write_cache_file=1';
@@ -660,13 +729,155 @@ const synthElevenlabs = async(logger, {credentials, options, stats, language, vo
   }
 };
 
-const synthWhisper = async(logger, {credentials, stats, voice, text, renderForCaching}) => {
+const synthPlayHT = async(logger, {
-  const {api_key, model_id, baseURL, timeout, speed} = credentials;
+  credentials, options, stats, voice, text, renderForCaching, disableTtsStreaming
-  /* if the env is set to stream then bag out, unless we are specifically rendering to generate a cache file */
+}) => {
-  if (!process.env.JAMBONES_DISABLE_TTS_STREAMING && !renderForCaching) {
+  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 synthRimelabs = 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 (!process.env.JAMBONES_DISABLE_TTS_STREAMING && !renderForCaching && !disableTtsStreaming) {
     let params = '';
     params += `{api_key=${api_key}`;
     params += `,model_id=${model_id}`;
+    params += ',vendor=rimelabs';
+    params += `,voice=${voice}`;
+    params += ',write_cache_file=1';
+    if (opts.speedAlpha) params += `,speed_alpha=${opts.speedAlpha}`;
+    if (opts.reduceLatency) params += `,reduce_latency=${opts.reduceLatency}`;
+    params += '}';
+
+    return {
+      filePath: `say:${params}${text.replace(/\n/g, ' ').replace(/\r/g, ' ')}`,
+      servedFromCache: false,
+      rtt: 0
+    };
+  }
+
+  try {
+    const post = bent('https://users.rime.ai', 'POST', 'buffer', {
+      'Authorization': `Bearer ${api_key}`,
+      'Accept': 'audio/mp3',
+      'Content-Type': 'application/json'
+    });
+    const mp3 = await post('/v1/rime-tts', {
+      speaker: voice,
+      text,
+      modelId: model_id,
+      samplingRate: 8000,
+      ...opts
+    });
+    return mp3;
+  } catch (err) {
+    logger.info({err}, 'synth rimelabs returned error');
+    stats.increment('tts.count', ['vendor:rimelabs', 'accepted:no']);
+    throw err;
+  }
+};
+const synthVerbio = async(client, logger, {credentials, stats, voice, text, renderForCaching, disableTtsStreaming}) => {
+  //https://doc.speechcenter.verbio.com/#tag/Text-To-Speech-REST-API
+  if (text.length > 2000) {
+    throw new Error('Verbio cannot synthesize for the text length larger than 2000 characters');
+  }
+  const token = await getVerbioAccessToken(client, logger, credentials);
+  if (!process.env.JAMBONES_DISABLE_TTS_STREAMING && !renderForCaching && !disableTtsStreaming) {
+    let params = '';
+    params += `{access_token=${token.access_token}`;
+    params += ',vendor=verbio';
+    params += `,voice=${voice}`;
+    params += ',write_cache_file=1';
+    params += '}';
+
+    return {
+      filePath: `say:${params}${text.replace(/\n/g, ' ')}`,
+      servedFromCache: false,
+      rtt: 0
+    };
+  }
+
+  try {
+    const post = bent('https://us.rest.speechcenter.verbio.com', 'POST', 'buffer', {
+      'Authorization': `Bearer ${token.access_token}`,
+      'User-Agent': 'jambonz',
+      'Content-Type': 'application/json'
+    });
+    const r8 = await post('/api/v1/synthesize', {
+      voice_id: voice,
+      output_sample_rate: '8k',
+      output_encoding: 'pcm16',
+      text
+    });
+    return r8;
+  } catch (err) {
+    logger.info({err}, 'synth Verbio returned error');
+    stats.increment('tts.count', ['vendor:verbio', 'accepted:no']);
+    throw err;
+  }
+};
+
+const synthWhisper = async(logger, {credentials, stats, voice, text, renderForCaching, disableTtsStreaming}) => {
+  const {api_key, model_id, baseURL, timeout, speed} = credentials;
+  /* if the env is set to stream then bag out, unless we are specifically rendering to generate a cache file */
+  if (!process.env.JAMBONES_DISABLE_TTS_STREAMING && !renderForCaching && !disableTtsStreaming) {
+    let params = '';
+    params += `{api_key=${api_key}`;
+    params += `,model_id=${model_id}`;
+    params += ',vendor=whisper';
     params += `,voice=${voice}`;
     params += ',write_cache_file=1';
     if (speed) params += `,speed=${speed}`;
@@ -699,10 +910,24 @@ const synthWhisper = async(logger, {credentials, stats, voice, text, renderForCa
   }
 };
 
-const synthDeepgram = async(logger, {credentials, stats, model, text}) => {
+const synthDeepgram = async(logger, {credentials, stats, model, text, renderForCaching, disableTtsStreaming}) => {
   const {api_key} = credentials;
+  if (!process.env.JAMBONES_DISABLE_TTS_STREAMING && !renderForCaching && !disableTtsStreaming) {
+    let params = '';
+    params += `{api_key=${api_key}`;
+    params += ',vendor=deepgram';
+    params += `,voice=${model}`;
+    params += ',write_cache_file=1';
+    params += '}';
+
+    return {
+      filePath: `say:${params}${text.replace(/\n/g, ' ')}`,
+      servedFromCache: false,
+      rtt: 0
+    };
+  }
   try {
-    const post = bent('https://api.beta.deepgram.com', 'POST', 'buffer', {
+    const post = bent('https://api.deepgram.com', 'POST', 'buffer', {
       'Authorization': `Token ${api_key}`,
       'Accept': 'audio/mpeg',
       'Content-Type': 'application/json'

lib/utils.js

@@ -3,10 +3,10 @@ const {SynthesizerClient} = require('../stubs/nuance/synthesizer_grpc_pb');
 const {RivaSpeechSynthesisClient} = require('../stubs/riva/proto/riva_tts_grpc_pb');
 const {Pool} = require('undici');
 const pool = new Pool('https://auth.crt.nuance.com');
-const HTTP_TIMEOUT = 5000;
 const NUANCE_AUTH_ENDPOINT = 'tts.api.nuance.com:443';
 const grpc = require('@grpc/grpc-js');
 const formurlencoded = require('form-urlencoded');
+const { HTTP_TIMEOUT } = require('./constants');
 
 const debug = require('debug')('jambonz:realtimedb-helpers');
 /**
@@ -49,6 +49,12 @@ function makeAwsKey(awsAccessKeyId) {
   return `aws:${hash.digest('hex')}`;
 }
 
+function makeVerbioKey(client_id) {
+  const hash = crypto.createHash('sha1');
+  hash.update(client_id);
+  return `verbio:${hash.digest('hex')}`;
+}
+
 function makeNuanceKey(clientId, secret, scope) {
   const hash = crypto.createHash('sha1');
   hash.update(`${clientId}:${secret}:${scope}`);
@@ -117,6 +123,7 @@ module.exports = {
   makeNuanceKey,
   makeIbmKey,
   makeAwsKey,
+  makeVerbioKey,
   getNuanceAccessToken,
   createNuanceClient,
   createKryptonClient,

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@jambonz/speech-utils",
-  "version": "0.0.42",
+  "version": "0.1.1",
   "lockfileVersion": 2,
   "requires": true,
   "packages": {
     "": {
       "name": "@jambonz/speech-utils",
-      "version": "0.0.42",
+      "version": "0.1.1",
       "license": "MIT",
       "dependencies": {
         "@aws-sdk/client-polly": "^3.496.0",
@@ -19,7 +19,7 @@
         "form-urlencoded": "^6.1.4",
         "google-protobuf": "^3.21.2",
         "ibm-watson": "^8.0.0",
-        "microsoft-cognitiveservices-speech-sdk": "1.34.0",
+        "microsoft-cognitiveservices-speech-sdk": "1.36.0",
         "openai": "^4.25.0",
         "undici": "^6.4.0"
       },
@@ -1124,14 +1124,6 @@
         "node": "^12.22.0 || ^14.17.0 || >=16.0.0"
       }
     },
-    "node_modules/@fastify/busboy": {
-      "version": "2.1.0",
-      "resolved": "https://registry.npmjs.org/@fastify/busboy/-/busboy-2.1.0.tgz",
-      "integrity": "sha512-+KpH+QxZU7O4675t3mnkQKcZZg56u+K/Ct2K+N2AZYNVK8kyeo/bI18tI8aPm3tvNNRyTWfj6s5tnGNlcbQRsA==",
-      "engines": {
-        "node": ">=14"
-      }
-    },
     "node_modules/@google-cloud/text-to-speech": {
       "version": "5.0.2",
       "resolved": "https://registry.npmjs.org/@google-cloud/text-to-speech/-/text-to-speech-5.0.2.tgz",
@@ -3125,13 +3117,14 @@
       }
     },
     "node_modules/es5-ext": {
-      "version": "0.10.62",
+      "version": "0.10.64",
-      "resolved": "https://registry.npmjs.org/es5-ext/-/es5-ext-0.10.62.tgz",
+      "resolved": "https://registry.npmjs.org/es5-ext/-/es5-ext-0.10.64.tgz",
-      "integrity": "sha512-BHLqn0klhEpnOKSrzn/Xsz2UIW8j+cGmo9JLzr8BiUapV8hPL9+FliFqjwr9ngW7jWdnxv6eO+/LqyhJVqgrjA==",
+      "integrity": "sha512-p2snDhiLaXe6dahss1LddxqEm+SkuDvV8dnIQG0MWjyHpcMNfXKPE+/Cc0y+PhxJX3A4xGNeFCj5oc0BUh6deg==",
       "hasInstallScript": true,
       "dependencies": {
         "es6-iterator": "^2.0.3",
         "es6-symbol": "^3.1.3",
+        "esniff": "^2.0.1",
         "next-tick": "^1.1.0"
       },
       "engines": {
@@ -3278,6 +3271,25 @@
         "url": "https://opencollective.com/eslint"
       }
     },
+    "node_modules/esniff": {
+      "version": "2.0.1",
+      "resolved": "https://registry.npmjs.org/esniff/-/esniff-2.0.1.tgz",
+      "integrity": "sha512-kTUIGKQ/mDPFoJ0oVfcmyJn4iBDRptjNVIzwIFR7tqWXdVI9xfA2RMwY/gbSpJG3lkdWNEjLap/NqVHZiJsdfg==",
+      "dependencies": {
+        "d": "^1.0.1",
+        "es5-ext": "^0.10.62",
+        "event-emitter": "^0.3.5",
+        "type": "^2.7.2"
+      },
+      "engines": {
+        "node": ">=0.10"
+      }
+    },
+    "node_modules/esniff/node_modules/type": {
+      "version": "2.7.2",
+      "resolved": "https://registry.npmjs.org/type/-/type-2.7.2.tgz",
+      "integrity": "sha512-dzlvlNlt6AXU7EBSfpAscydQ7gXB+pPGsPnfJnZpiNJBDj7IaJzQlBZYGdEi4R9HmPdBv2XmWJ6YUtoTa7lmCw=="
+    },
     "node_modules/espree": {
       "version": "9.6.1",
       "resolved": "https://registry.npmjs.org/espree/-/espree-9.6.1.tgz",
@@ -3350,6 +3362,15 @@
         "node": ">=0.10.0"
       }
     },
+    "node_modules/event-emitter": {
+      "version": "0.3.5",
+      "resolved": "https://registry.npmjs.org/event-emitter/-/event-emitter-0.3.5.tgz",
+      "integrity": "sha512-D9rRn9y7kLPnJ+hMq7S/nhvoKwwvVJahBi2BPmx3bvbsEdK3W9ii8cBSGjP+72/LnM4n6fo3+dkCX5FeTQruXA==",
+      "dependencies": {
+        "d": "1",
+        "es5-ext": "~0.10.14"
+      }
+    },
     "node_modules/event-target-shim": {
       "version": "5.0.1",
       "resolved": "https://registry.npmjs.org/event-target-shim/-/event-target-shim-5.0.1.tgz",
@@ -3551,9 +3572,9 @@
       "dev": true
     },
     "node_modules/follow-redirects": {
-      "version": "1.15.5",
+      "version": "1.15.6",
-      "resolved": "https://registry.npmjs.org/follow-redirects/-/follow-redirects-1.15.5.tgz",
+      "resolved": "https://registry.npmjs.org/follow-redirects/-/follow-redirects-1.15.6.tgz",
-      "integrity": "sha512-vSFWUON1B+yAw1VN4xMfxgn5fTUiaOzAJCKBwIIgT/+7CuGy9+r+5gITvP62j3RmaD5Ph65UaERdOSRGUzZtgw==",
+      "integrity": "sha512-wWN62YITEaOpSK584EZXJafH1AGpO8RVgElfkuXbTOrPX4fIfOyEpW/CsiNd8JdYrAoOvafRTOEnvsO++qCqFA==",
       "funding": [
         {
           "type": "individual",
@@ -5084,9 +5105,9 @@
       }
     },
     "node_modules/microsoft-cognitiveservices-speech-sdk": {
-      "version": "1.34.0",
+      "version": "1.36.0",
-      "resolved": "https://registry.npmjs.org/microsoft-cognitiveservices-speech-sdk/-/microsoft-cognitiveservices-speech-sdk-1.34.0.tgz",
+      "resolved": "https://registry.npmjs.org/microsoft-cognitiveservices-speech-sdk/-/microsoft-cognitiveservices-speech-sdk-1.36.0.tgz",
-      "integrity": "sha512-WAR0YqouRzVux2kI+f5wTPC6NyJgIVC1g65d79dJ9I32WPJs2kK+eb/BMB6mhSdCjackO5FsrW7JLaQ/vB1heQ==",
+      "integrity": "sha512-wPxuEXgjLdqMMIrdBtl8jquGahLV19LQE0ie8MI/PcBcNLG5buVzwS2rQEyHMsRGx+C/4OdBo1ROdNIUzCm4Lg==",
       "dependencies": {
         "@types/webrtc": "^0.0.37",
         "agent-base": "^6.0.1",
@@ -6851,12 +6872,9 @@
       }
     },
     "node_modules/undici": {
-      "version": "6.4.0",
+      "version": "6.11.1",
-      "resolved": "https://registry.npmjs.org/undici/-/undici-6.4.0.tgz",
+      "resolved": "https://registry.npmjs.org/undici/-/undici-6.11.1.tgz",
-      "integrity": "sha512-wYaKgftNqf6Je7JQ51YzkEkEevzOgM7at5JytKO7BjaURQpERW8edQSMrr2xb+Yv4U8Yg47J24+lc9+NbeXMFA==",
+      "integrity": "sha512-KyhzaLJnV1qa3BSHdj4AZ2ndqI0QWPxYzaIOio0WzcEJB9gvuysprJSLtpvc2D9mhR9jPDUk7xlJlZbH2KR5iw==",
-      "dependencies": {
-        "@fastify/busboy": "^2.0.0"
-      },
       "engines": {
         "node": ">=18.0"
       }
@@ -8092,11 +8110,6 @@
       "integrity": "sha512-gMsVel9D7f2HLkBma9VbtzZRehRogVRfbr++f06nL2vnCGCNlzOD+/MUov/F4p8myyAHspEhVobgjpX64q5m6A==",
       "dev": true
     },
-    "@fastify/busboy": {
-      "version": "2.1.0",
-      "resolved": "https://registry.npmjs.org/@fastify/busboy/-/busboy-2.1.0.tgz",
-      "integrity": "sha512-+KpH+QxZU7O4675t3mnkQKcZZg56u+K/Ct2K+N2AZYNVK8kyeo/bI18tI8aPm3tvNNRyTWfj6s5tnGNlcbQRsA=="
-    },
     "@google-cloud/text-to-speech": {
       "version": "5.0.2",
       "resolved": "https://registry.npmjs.org/@google-cloud/text-to-speech/-/text-to-speech-5.0.2.tgz",
@@ -9652,12 +9665,13 @@
       }
     },
     "es5-ext": {
-      "version": "0.10.62",
+      "version": "0.10.64",
-      "resolved": "https://registry.npmjs.org/es5-ext/-/es5-ext-0.10.62.tgz",
+      "resolved": "https://registry.npmjs.org/es5-ext/-/es5-ext-0.10.64.tgz",
-      "integrity": "sha512-BHLqn0klhEpnOKSrzn/Xsz2UIW8j+cGmo9JLzr8BiUapV8hPL9+FliFqjwr9ngW7jWdnxv6eO+/LqyhJVqgrjA==",
+      "integrity": "sha512-p2snDhiLaXe6dahss1LddxqEm+SkuDvV8dnIQG0MWjyHpcMNfXKPE+/Cc0y+PhxJX3A4xGNeFCj5oc0BUh6deg==",
       "requires": {
         "es6-iterator": "^2.0.3",
         "es6-symbol": "^3.1.3",
+        "esniff": "^2.0.1",
         "next-tick": "^1.1.0"
       }
     },
@@ -9766,6 +9780,24 @@
       "integrity": "sha512-wpc+LXeiyiisxPlEkUzU6svyS1frIO3Mgxj1fdy7Pm8Ygzguax2N3Fa/D/ag1WqbOprdI+uY6wMUl8/a2G+iag==",
       "dev": true
     },
+    "esniff": {
+      "version": "2.0.1",
+      "resolved": "https://registry.npmjs.org/esniff/-/esniff-2.0.1.tgz",
+      "integrity": "sha512-kTUIGKQ/mDPFoJ0oVfcmyJn4iBDRptjNVIzwIFR7tqWXdVI9xfA2RMwY/gbSpJG3lkdWNEjLap/NqVHZiJsdfg==",
+      "requires": {
+        "d": "^1.0.1",
+        "es5-ext": "^0.10.62",
+        "event-emitter": "^0.3.5",
+        "type": "^2.7.2"
+      },
+      "dependencies": {
+        "type": {
+          "version": "2.7.2",
+          "resolved": "https://registry.npmjs.org/type/-/type-2.7.2.tgz",
+          "integrity": "sha512-dzlvlNlt6AXU7EBSfpAscydQ7gXB+pPGsPnfJnZpiNJBDj7IaJzQlBZYGdEi4R9HmPdBv2XmWJ6YUtoTa7lmCw=="
+        }
+      }
+    },
     "espree": {
       "version": "9.6.1",
       "resolved": "https://registry.npmjs.org/espree/-/espree-9.6.1.tgz",
@@ -9813,6 +9845,15 @@
       "integrity": "sha512-kVscqXk4OCp68SZ0dkgEKVi6/8ij300KBWTJq32P/dYeWTSwK41WyTxalN1eRmA5Z9UU/LX9D7FWSmV9SAYx6g==",
       "dev": true
     },
+    "event-emitter": {
+      "version": "0.3.5",
+      "resolved": "https://registry.npmjs.org/event-emitter/-/event-emitter-0.3.5.tgz",
+      "integrity": "sha512-D9rRn9y7kLPnJ+hMq7S/nhvoKwwvVJahBi2BPmx3bvbsEdK3W9ii8cBSGjP+72/LnM4n6fo3+dkCX5FeTQruXA==",
+      "requires": {
+        "d": "1",
+        "es5-ext": "~0.10.14"
+      }
+    },
     "event-target-shim": {
       "version": "5.0.1",
       "resolved": "https://registry.npmjs.org/event-target-shim/-/event-target-shim-5.0.1.tgz",
@@ -9964,9 +10005,9 @@
       "dev": true
     },
     "follow-redirects": {
-      "version": "1.15.5",
+      "version": "1.15.6",
-      "resolved": "https://registry.npmjs.org/follow-redirects/-/follow-redirects-1.15.5.tgz",
+      "resolved": "https://registry.npmjs.org/follow-redirects/-/follow-redirects-1.15.6.tgz",
-      "integrity": "sha512-vSFWUON1B+yAw1VN4xMfxgn5fTUiaOzAJCKBwIIgT/+7CuGy9+r+5gITvP62j3RmaD5Ph65UaERdOSRGUzZtgw=="
+      "integrity": "sha512-wWN62YITEaOpSK584EZXJafH1AGpO8RVgElfkuXbTOrPX4fIfOyEpW/CsiNd8JdYrAoOvafRTOEnvsO++qCqFA=="
     },
     "for-each": {
       "version": "0.3.3",
@@ -11108,9 +11149,9 @@
       }
     },
     "microsoft-cognitiveservices-speech-sdk": {
-      "version": "1.34.0",
+      "version": "1.36.0",
-      "resolved": "https://registry.npmjs.org/microsoft-cognitiveservices-speech-sdk/-/microsoft-cognitiveservices-speech-sdk-1.34.0.tgz",
+      "resolved": "https://registry.npmjs.org/microsoft-cognitiveservices-speech-sdk/-/microsoft-cognitiveservices-speech-sdk-1.36.0.tgz",
-      "integrity": "sha512-WAR0YqouRzVux2kI+f5wTPC6NyJgIVC1g65d79dJ9I32WPJs2kK+eb/BMB6mhSdCjackO5FsrW7JLaQ/vB1heQ==",
+      "integrity": "sha512-wPxuEXgjLdqMMIrdBtl8jquGahLV19LQE0ie8MI/PcBcNLG5buVzwS2rQEyHMsRGx+C/4OdBo1ROdNIUzCm4Lg==",
       "requires": {
         "@types/webrtc": "^0.0.37",
         "agent-base": "^6.0.1",
@@ -12405,12 +12446,9 @@
       }
     },
     "undici": {
-      "version": "6.4.0",
+      "version": "6.11.1",
-      "resolved": "https://registry.npmjs.org/undici/-/undici-6.4.0.tgz",
+      "resolved": "https://registry.npmjs.org/undici/-/undici-6.11.1.tgz",
-      "integrity": "sha512-wYaKgftNqf6Je7JQ51YzkEkEevzOgM7at5JytKO7BjaURQpERW8edQSMrr2xb+Yv4U8Yg47J24+lc9+NbeXMFA==",
+      "integrity": "sha512-KyhzaLJnV1qa3BSHdj4AZ2ndqI0QWPxYzaIOio0WzcEJB9gvuysprJSLtpvc2D9mhR9jPDUk7xlJlZbH2KR5iw=="
-      "requires": {
-        "@fastify/busboy": "^2.0.0"
-      }
     },
     "undici-types": {
       "version": "5.26.5",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jambonz/speech-utils",
-  "version": "0.0.42",
+  "version": "0.1.1",
   "description": "TTS-related speech utilities for jambonz",
   "main": "index.js",
   "author": "Dave Horton",
@@ -34,7 +34,7 @@
     "form-urlencoded": "^6.1.4",
     "google-protobuf": "^3.21.2",
     "ibm-watson": "^8.0.0",
-    "microsoft-cognitiveservices-speech-sdk": "1.34.0",
+    "microsoft-cognitiveservices-speech-sdk": "1.36.0",
     "openai": "^4.25.0",
     "undici": "^6.4.0"
   },

test/list-voices.js

@@ -12,6 +12,32 @@ const stats = {
   histogram: () => {}
 };
 
+test('Verbio - get Access key and voices', async(t) => {
+  const fn = require('..');
+  const {client, getTtsVoices, getVerbioAccessToken} = fn(opts, logger);
+  if (!process.env.VERBIO_CLIENT_ID || !process.env.VERBIO_CLIENT_SECRET) {
+    t.pass('skipping Verbio test since no Verbio Keys provided');
+    t.end();
+    client.quit();
+    return;
+  }
+
+  try {
+    const credentials = {
+      client_id: process.env.VERBIO_CLIENT_ID,
+      client_secret: process.env.VERBIO_CLIENT_SECRET
+    };
+    let obj = await getVerbioAccessToken(credentials);
+    t.ok(obj.access_token , 'successfully received access token not from cache');
+    const voices = await getTtsVoices({vendor: 'verbio', credentials});
+    t.ok(voices && voices.length != 0, 'successfully received verbio voices');
+  } catch (err) {
+    console.error(err);
+    t.end(err);
+  }
+  client.quit();
+});
+
 test('IBM - create access key', async(t) => {
   const fn = require('..');
   const {client, getIbmAccessToken} = fn(opts, logger);

test/synth.js

@@ -162,6 +162,33 @@ test('AWS speech synth tests', async(t) => {
   client.quit();
 });
 
+test('AWS speech synth tests by RoleArn', async(t) => {
+  const fn = require('..');
+  const {synthAudio, client} = fn(opts, logger);
+
+  if (!process.env.AWS_ROLE_ARN || !process.env.AWS_REGION) {
+    t.pass('skipping AWS speech synth tests by RoleArn since AWS_ROLE_ARN or AWS_REGION not provided');
+    return t.end();
+  }
+  try {
+    let opts = await synthAudio(stats, {
+      vendor: 'aws',
+      credentials: {
+        roleArn: process.env.AWS_ROLE_ARN,
+        region: process.env.AWS_REGION,
+      },
+      language: 'en-US',
+      voice: 'Joey',
+      text: 'This is a test.  This is only a test',
+    });
+    t.ok(!opts.servedFromCache, `successfully synthesized aws by roleArn audio to ${opts.filePath}`);
+  } catch (err) {
+    console.error(err);
+    t.end(err);
+  }
+  client.quit();
+});
+
 test('Azure speech synth tests', async(t) => {
   const fn = require('..');
   const {synthAudio, client} = fn(opts, logger);
@@ -188,6 +215,7 @@ test('Azure speech synth tests', async(t) => {
       language: 'en-US',
       voice: 'en-US-ChristopherNeural',
       text: longText,
+      renderForCaching: true
     });
     t.ok(!opts.servedFromCache, `successfully synthesized microsoft audio to ${opts.filePath}`);
     if (process.env.JAMBONES_HTTP_PROXY_IP && process.env.JAMBONES_HTTP_PROXY_PORT) {
@@ -203,6 +231,7 @@ test('Azure speech synth tests', async(t) => {
       language: 'en-US',
       voice: 'en-US-ChristopherNeural',
       text: longText,
+      renderForCaching: true
     });
     t.ok(opts.servedFromCache, `successfully retrieved microsoft audio from cache ${opts.filePath}`);
   } catch (err) {
@@ -212,6 +241,58 @@ test('Azure speech synth tests', async(t) => {
   client.quit();
 });
 
+test('Azure SSML tests', async(t) => {
+  const fn = require('..');
+  const {synthAudio, client} = fn(opts, logger);
+
+  if (!process.env.MICROSOFT_API_KEY || !process.env.MICROSOFT_REGION) {
+    t.pass('skipping Microsoft speech synth tests since MICROSOFT_API_KEY or MICROSOFT_REGION not provided');
+    return t.end();
+  }
+  try {
+    const text = `<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="https://www.w3.org/2001/mstts" xml:lang="en-US">
+    <voice name="en-US-JennyMultilingualNeural">
+    <mstts:express-as style="cheerful" styledegree="2">That'd be just amazing!
+    </mstts:express-as>
+    </voice>
+    </speak>`;
+
+    let opts = await synthAudio(stats, {
+      vendor: 'microsoft',
+      credentials: {
+        api_key: process.env.MICROSOFT_API_KEY,
+        region: process.env.MICROSOFT_REGION,
+      },
+      language: 'en-US',
+      voice: 'en-US-ChristopherNeural',
+      text,
+      renderForCaching: true
+    });
+    t.ok(!opts.servedFromCache, `successfully synthesized microsoft audio to ${opts.filePath}`);
+    if (process.env.JAMBONES_HTTP_PROXY_IP && process.env.JAMBONES_HTTP_PROXY_PORT) {
+      t.pass('successfully used proxy to reach microsoft tts service');
+    }
+
+    opts = await synthAudio(stats, {
+      vendor: 'microsoft',
+      credentials: {
+        api_key: process.env.MICROSOFT_API_KEY,
+        region: process.env.MICROSOFT_REGION,
+      },
+      language: 'en-US',
+      voice: 'en-US-ChristopherNeural',
+      text,
+      renderForCaching: true
+    });
+    t.ok(opts.servedFromCache, `successfully retrieved microsoft audio from cache ${opts.filePath}`);
+  } catch (err) {
+    console.error(err);
+    t.end(err);
+  }
+  client.quit();
+});
+
+
 test('Azure custom voice speech synth tests', async(t) => {
   const fn = require('..');
   const {synthAudio, client} = fn(opts, logger);
@@ -233,6 +314,7 @@ test('Azure custom voice speech synth tests', async(t) => {
       language: 'en-US',
       voice: process.env.MICROSOFT_CUSTOM_VOICE,
       text,
+      renderForCaching: true
     });
     t.ok(!opts.servedFromCache, `successfully synthesized microsoft audio to ${opts.filePath}`);
 
@@ -247,6 +329,7 @@ test('Azure custom voice speech synth tests', async(t) => {
       language: 'en-US',
       voice: process.env.MICROSOFT_CUSTOM_VOICE,
       text,
+      renderForCaching: true
     });
     t.ok(opts.servedFromCache, `successfully retrieved microsoft custom voice audio from cache ${opts.filePath}`);
   } catch (err) {
@@ -493,6 +576,81 @@ 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 playht eleven audio to ${opts.filePath}`);
+
+  } catch (err) {
+    console.error(JSON.stringify(err));
+    t.end(err);
+  }
+  client.quit();
+});
+
+test('rimelabs speech synth tests', async(t) => {
+  const fn = require('..');
+  const {synthAudio, client} = fn(opts, logger);
+
+  if (!process.env.RIMELABS_API_KEY) {
+    t.pass('skipping rimelabs speech synth tests since RIMELABS_API_KEY is not provided');
+    return t.end();
+  }
+  const text = 'Hi there and welcome to jambones!';
+  try {
+    let opts = await synthAudio(stats, {
+      vendor: 'rimelabs',
+      credentials: {
+        api_key: process.env.RIMELABS_API_KEY,
+        model_id: 'mist',
+        options: JSON.stringify({
+          speedAlpha: 1.0,
+          reduceLatency: false
+        })
+      },
+      language: 'en-US',
+      voice: 'amber',
+      text,
+      renderForCaching: true
+    });
+    t.ok(!opts.servedFromCache, `successfully synthesized rimelabs 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);
@@ -512,6 +670,40 @@ test('whisper speech synth tests', async(t) => {
       language: 'en-US',
       voice: 'alloy',
       text,
+      renderForCaching: true
+    });
+    t.ok(!opts.servedFromCache, `successfully synthesized whisper audio to ${opts.filePath}`);
+
+  } catch (err) {
+    console.error(JSON.stringify(err));
+    t.end(err);
+  }
+  client.quit();
+});
+
+test('Verbio speech synth tests', async(t) => {
+  const fn = require('..');
+  const {synthAudio, client} = fn(opts, logger);
+
+  if (!process.env.VERBIO_CLIENT_ID || !process.env.VERBIO_CLIENT_SECRET) {
+    t.pass('skipping Verbio Synthesize test since no Verbio Keys provided');
+    t.end();
+    client.quit();
+    return;
+  }
+
+  const text = 'Hi there and welcome to jambones!';
+  try {
+    let opts = await synthAudio(stats, {
+      vendor: 'verbio',
+      credentials: {
+        client_id: process.env.VERBIO_CLIENT_ID,
+        client_secret: process.env.VERBIO_CLIENT_SECRET
+      },
+      language: 'en-US',
+      voice: 'tommy_en-us',
+      text,
+      renderForCaching: true
     });
     t.ok(!opts.servedFromCache, `successfully synthesized whisper audio to ${opts.filePath}`);
 
@@ -537,8 +729,9 @@ test('Deepgram speech synth tests', async(t) => {
       credentials: {
         api_key: process.env.DEEPGRAM_API_KEY
       },
-      model: 'alpha-asteria-en-v2',
+      model: 'aura-asteria-en',
       text,
+      renderForCaching: true
     });
     t.ok(!opts.servedFromCache, `successfully synthesized deepgram audio to ${opts.filePath}`);