@jambonz/speech-utils 1.0.4 → 1.0.7

package/index.js

@@ -14,8 +14,6 @@ module.exports = (opts, 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, createHash, retrieveHash, logger),
-    getVerbioAccessToken: require('./lib/get-verbio-token').bind(null, client, logger),
-    getNuanceAccessToken: require('./lib/get-nuance-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, createHash, retrieveHash, logger),

package/lib/get-tts-voices.js

@@ -1,74 +1,8 @@
 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 {noopLogger} = require('./utils');
 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('./config');
-const verbioVoicePool = new Pool('https://us.rest.speechcenter.verbio.com');
-
-const getNuanceVoices = async(client, logger, credentials) => {
-  const {client_id: clientId, secret: secret, nuance_tts_uri} = credentials;
-
-  return new Promise(async(resolve, reject) => {
-    /* get a nuance access token */
-    let token, nuanceClient;
-    try {
-      if (nuance_tts_uri) {
-        nuanceClient = await createKryptonClient(nuance_tts_uri);
-      }
-      else {
-        const access_token = await getNuanceAccessToken(client, logger, clientId, secret, 'tts');
-        token = access_token.access_token;
-        nuanceClient = await createNuanceClient(token);
-      }
-    } catch (err) {
-      logger.error({err}, 'getTtsVoices: error retrieving access token');
-      return reject(err);
-    }
-    /* retrieve all voices */
-    const v = new Voice();
-    const request = new GetVoicesRequest();
-    request.setVoice(v);
-
-    nuanceClient.getVoices(request, (err, response) => {
-      if (err) {
-        logger.error({err, clientId, secret, token}, 'getTtsVoices: error retrieving voices');
-        return reject(err);
-      }
-
-      /* return all the voices that are not restricted and eliminate duplicates */
-      const voices = response.getVoicesList()
-        .map((v) => {
-          return {
-            language: v.getLanguage(),
-            name: v.getName(),
-            model: v.getModel(),
-            gender: v.getGender() === 1 ? 'male' : 'female',
-            restricted: v.getRestricted()
-          };
-        });
-      const v = voices
-        .filter((v) => v.restricted === false)
-        .map((v) => {
-          delete v.restricted;
-          return v;
-        })
-        .sort((a, b) => {
-          if (a.language < b.language) return -1;
-          if (a.language > b.language) return 1;
-          if (a.name < b.name) return -1;
-          return 1;
-        });
-      const arr = [...new Set(v.map((v) => JSON.stringify(v)))]
-        .map((v) => JSON.parse(v));
-      resolve(arr);
-    });
-  });
-};
 
 const getGoogleVoices = async(_client, logger, credentials) => {
   const client = new ttsGoogle.TextToSpeechClient({credentials});
@@ -109,26 +43,6 @@ const getAwsVoices = async(_client, createHash, retrieveHash, logger, credential
   }
 };
 
-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
@@ -148,19 +62,15 @@ const getVerbioVoices = async(client, logger, credentials) => {
 async function getTtsVoices(client, createHash, retrieveHash, logger, {vendor, credentials}) {
   logger = logger || noopLogger;
 
-  assert.ok(['nuance', 'google', 'aws', 'polly', 'verbio'].includes(vendor),
+  assert.ok(['google', 'aws', 'polly'].includes(vendor),
     `getTtsVoices not supported for vendor ${vendor}`);
 
   switch (vendor) {
-    case 'nuance':
-      return getNuanceVoices(client, logger, credentials);
     case 'google':
       return getGoogleVoices(client, logger, credentials);
     case 'aws':
     case 'polly':
       return getAwsVoices(client, createHash, retrieveHash, logger, credentials);
-    case 'verbio':
-      return getVerbioVoices(client, logger, credentials);
     default:
       break;
   }

package/lib/synth-audio.js

@@ -16,26 +16,10 @@ const {
 } = sdk;
 const {
   makeSynthKey,
-  createNuanceClient,
-  createKryptonClient,
   createRivaClient,
   noopLogger,
-  makeFilePath,
-  makePlayhtKey
+  makeFilePath
 } = require('./utils');
-const getNuanceAccessToken = require('./get-nuance-access-token');
-const getVerbioAccessToken = require('./get-verbio-token');
-const {
-  SynthesisRequest,
-  Voice,
-  AudioFormat,
-  AudioParameters,
-  PCM,
-  Input,
-  Text,
-  SSML,
-  EventParameters
-} = require('../stubs/nuance/synthesizer_pb');
 const {SynthesizeSpeechRequest} = require('../stubs/riva/proto/riva_tts_pb');
 const {AudioEncoding} = require('../stubs/riva/proto/riva_audio_pb');
 const debug = require('debug')('jambonz:realtimedb-helpers');
@@ -95,10 +79,10 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
   let rtt;
   logger = logger || noopLogger;
 
-  assert.ok(['google', 'aws', 'polly', 'microsoft', 'wellsaid', 'nuance', 'nvidia', 'elevenlabs',
-    'whisper', 'deepgram', 'playht', 'rimelabs', 'verbio', 'cartesia', 'inworld', 'resemble'].includes(vendor) ||
+  assert.ok(['google', 'aws', 'polly', 'microsoft', 'wellsaid', 'nvidia', 'elevenlabs',
+    'whisper', 'deepgram', 'rimelabs', 'cartesia', 'inworld', 'resemble', 'murf'].includes(vendor) ||
   vendor.startsWith('custom'),
-  `synthAudio supported vendors are google, aws, microsoft, nuance, nvidia and wellsaid ..etc, not ${vendor}`);
+  `synthAudio supported vendors are google, aws, microsoft, nvidia and wellsaid ..etc, not ${vendor}`);
   if ('google' === vendor) {
     assert.ok(language, 'synthAudio requires language when google is used');
   }
@@ -109,13 +93,6 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
     assert.ok(language || deploymentId, 'synthAudio requires language when microsoft is used');
     assert.ok(voice || deploymentId, 'synthAudio requires voice when microsoft is used');
   }
-  else if ('nuance' === vendor) {
-    assert.ok(voice, 'synthAudio requires voice when nuance is used');
-    if (!credentials.nuance_tts_uri) {
-      assert.ok(credentials.client_id, 'synthAudio requires client_id in credentials when nuance is used');
-      assert.ok(credentials.secret, 'synthAudio requires client_id in credentials when nuance is used');
-    }
-  }
   else if ('nvidia' === vendor) {
     assert.ok(voice, 'synthAudio requires voice when nvidia is used');
     assert.ok(language, 'synthAudio requires language when nvidia is used');
@@ -129,11 +106,6 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
     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 ('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');
@@ -148,10 +120,6 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
     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');
   } else if ('deepgram' === vendor) {
     if (!credentials.deepgram_tts_uri) {
       assert.ok(credentials.api_key, 'synthAudio requires api_key when deepgram is used');
@@ -159,6 +127,9 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
   } else if ('cartesia' === vendor) {
     assert.ok(credentials.api_key, 'synthAudio requires api_key when cartesia is used');
     assert.ok(credentials.model_id, 'synthAudio requires model_id when cartesia is used');
+  } else if ('murf' === vendor) {
+    assert.ok(voice, 'synthAudio requires voice when murf is used');
+    assert.ok(credentials.api_key, 'synthAudio requires api_key when murf is used');
   } else if (vendor === 'resemble') {
     assert.ok(voice, 'synthAudio requires voice when resemble is used');
     assert.ok(credentials.api_key, 'synthAudio requires api_key when resemble is used');
@@ -216,10 +187,6 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
         audioData = await synthMicrosoft(logger, {credentials, stats, language, voice, key, text, deploymentId,
           renderForCaching, disableTtsStreaming, disableTtsCache});
         break;
-      case 'nuance':
-        model = model || 'enhanced';
-        audioData = await synthNuance(client, logger, {credentials, stats, voice, model, key, text});
-        break;
       case 'nvidia':
         audioData = await synthNvidia(client, logger, {credentials, stats, language, voice, model, key, text,
           renderForCaching, disableTtsStreaming, disableTtsCache});
@@ -232,11 +199,6 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
           credentials, options, stats, language, voice, key, text, renderForCaching, disableTtsStreaming,
           disableTtsCache});
         break;
-      case 'playht':
-        audioData = await synthPlayHT(client, logger, {
-          credentials, options, stats, language, voice, key, text, renderForCaching, disableTtsStreaming,
-          disableTtsCache});
-        break;
       case 'cartesia':
         audioData = await synthCartesia(logger, {
           credentials, options, stats, language, voice, key, text, renderForCaching, disableTtsStreaming,
@@ -252,16 +214,16 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
           credentials, options, stats, language, voice, key, text, renderForCaching, disableTtsStreaming,
           disableTtsCache});
         break;
+      case 'murf':
+        audioData = await synthMurf(logger, {
+          credentials, options, stats, language, voice, key, text, renderForCaching, disableTtsStreaming,
+          disableTtsCache});
+        break;
       case 'whisper':
         audioData = await synthWhisper(logger, {
           credentials, stats, voice, key, text, instructions, renderForCaching, disableTtsStreaming,
           disableTtsCache});
         break;
-      case 'verbio':
-        audioData = await synthVerbio(client, logger, {
-          credentials, stats, voice, key, text, renderForCaching, disableTtsStreaming, disableTtsCache});
-        if (audioData?.filePath) return audioData;
-        break;
       case 'deepgram':
         audioData = await synthDeepgram(logger, {credentials, stats, model, key, text,
           renderForCaching, disableTtsStreaming, disableTtsCache});
@@ -316,6 +278,7 @@ const synthPolly = async(createHash, retrieveHash, logger,
     params += `,playback_id=${key}`;
     params += `,write_cache_file=${disableTtsCache ? 0 : 1}`;
     params += ',vendor=aws';
+    params += `,voice=${voice}`;
     if (accessKeyId && secretAccessKey) {
       if (accessKeyId) params += `,accessKeyId=${accessKeyId}`;
       if (secretAccessKey) params += `,secretAccessKey=${secretAccessKey}`;
@@ -724,70 +687,6 @@ const synthWellSaid = async(logger, {credentials, stats, language, voice, gender
   }
 };
 
-const synthNuance = async(client, logger, {credentials, stats, voice, model, text}) => {
-  let nuanceClient;
-  const {client_id, secret, nuance_tts_uri} = credentials;
-  if (nuance_tts_uri) {
-    nuanceClient = await createKryptonClient(nuance_tts_uri);
-  }
-  else {
-    /* get a nuance access token */
-    const {access_token} = await getNuanceAccessToken(client, logger, client_id, secret, 'tts');
-    nuanceClient = await createNuanceClient(access_token);
-  }
-
-  const v = new Voice();
-  const p = new AudioParameters();
-  const f = new AudioFormat();
-  const pcm = new PCM();
-  const params  = new EventParameters();
-  const request = new SynthesisRequest();
-  const input = new Input();
-
-  if (text.startsWith('<speak')) {
-    const ssml = new SSML();
-    ssml.setText(text);
-    input.setSsml(ssml);
-  }
-  else {
-    const t = new Text();
-    t.setText(text);
-    input.setText(t);
-  }
-  const sampleRate = 8000;
-  pcm.setSampleRateHz(sampleRate);
-  f.setPcm(pcm);
-  p.setAudioFormat(f);
-  v.setName(voice);
-  v.setModel(model);
-  request.setVoice(v);
-  request.setAudioParams(p);
-  request.setInput(input);
-  request.setEventParams(params);
-  request.setUserId('jambonz');
-
-  return new Promise((resolve, reject) => {
-    nuanceClient.unarySynthesize(request, (err, response) => {
-      if (err) {
-        console.error(err);
-        return reject(err);
-      }
-      const status = response.getStatus();
-      const code = status.getCode();
-      if (code !== 200) {
-        const message = status.getMessage();
-        const details = status.getDetails();
-        return reject({code, message, details});
-      }
-      resolve({
-        audioContent: Buffer.from(response.getAudio()),
-        extension: 'r8',
-        sampleRate
-      });
-    });
-  });
-};
-
 const synthNvidia = async(client, logger, {
   credentials, stats, language,  voice, model, key, text, renderForCaching, disableTtsStreaming, disableTtsCache
 }) => {
@@ -953,101 +852,6 @@ const synthElevenlabs = async(logger, {
   }
 };
 
-const synthPlayHT = async(client, logger, {
-  credentials, options, stats, voice, language, key, text, renderForCaching, disableTtsStreaming, disableTtsCache
-}) => {
-  const {api_key, user_id, voice_engine, playht_tts_uri, options: credOpts} = credentials;
-  const opts = !!options && Object.keys(options).length !== 0 ? options : JSON.parse(credOpts || '{}');
-
-  let synthesizeUrl = playht_tts_uri ? `${playht_tts_uri}/api/v2/tts/stream` : 'https://api.play.ht/api/v2/tts/stream';
-  // If model is play3.0, the synthesizeUrl is got from authentication endpoint
-  if (voice_engine === 'Play3.0') {
-    try {
-      const post = bent('https://api.play.ht', 'POST', 'json', 201, {
-        'AUTHORIZATION': api_key,
-        'X-USER-ID': user_id,
-        'Accept': 'application/json'
-      });
-      const key = makePlayhtKey(api_key);
-      const url = await client.get(key);
-      if (!url) {
-        const {inference_address, expires_at_ms} = await post('/api/v3/auth');
-        synthesizeUrl = inference_address;
-        const expiry =  Math.floor((expires_at_ms - Date.now()) / 1000 - 30);
-        await client.set(key, inference_address, 'EX', expiry);
-      } else {
-        // Use cached URL
-        synthesizeUrl = url;
-      }
-    } catch (err) {
-      logger.info({err}, 'synth PlayHT returned error for authentication version 3.0');
-      stats.increment('tts.count', ['vendor:playht', 'accepted:no']);
-      throw err;
-    }
-  }
-
-  /* default to using the streaming interface, unless disabled by env var OR we want just a cache file */
-  if (!JAMBONES_DISABLE_TTS_STREAMING && !renderForCaching && !disableTtsStreaming) {
-    let params = '{';
-    params += `api_key=${api_key}`;
-    params += `,playback_id=${key}`;
-    params += `,user_id=${user_id}`;
-    params += ',vendor=playht';
-    params += `,voice=${voice}`;
-    params += `,voice_engine=${voice_engine}`;
-    params += `,synthesize_url=${synthesizeUrl}`;
-    params += `,write_cache_file=${disableTtsCache ? 0 : 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}`;
-    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=${opts.text_guidance}`;
-    if (opts.top_p) params += `,top_p=${opts.top_p}`;
-    if (opts.repetition_penalty) params += `,repetition_penalty=${opts.repetition_penalty}`;
-    params += '}';
-
-    return {
-      filePath: `say:${params}${text.replace(/\n/g, ' ').replace(/\r/g, ' ')}`,
-      servedFromCache: false,
-      rtt: 0
-    };
-  }
-
-  try {
-    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 audioContent = await post(synthesizeUrl, {
-      text,
-      ...(voice_engine === 'Play3.0' && { language }),
-      voice,
-      voice_engine,
-      output_format: 'mp3',
-      sample_rate: 8000,
-      ...opts
-    });
-    return {
-      audioContent,
-      extension: 'mp3',
-      sampleRate: 8000
-    };
-  } catch (err) {
-    logger.info({err}, 'synth PlayHT returned error');
-    stats.increment('tts.count', ['vendor:playht', 'accepted:no']);
-    throw err;
-  }
-};
-
 const synthInworld = async(logger, {
   credentials, options, stats, voice, key, text, renderForCaching, disableTtsStreaming, disableTtsCache
 }) => {
@@ -1173,54 +977,72 @@ const synthRimelabs = async(logger, {
     throw err;
   }
 };
-const synthVerbio = async(client, logger, {
-  credentials, stats, voice, key, text, renderForCaching, disableTtsStreaming, disableTtsCache
+
+const synthMurf = async(logger, {
+  credentials, options, stats, language, voice, key, text, renderForCaching, disableTtsStreaming, disableTtsCache
 }) => {
-  //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) {
+  const {api_key, model_id, api_uri, 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) {
+    /* param keys here must match mod_murf_tts's text_param handler */
     let params = '{';
-    params += `access_token=${token.access_token}`;
+    params += `api_key=${api_key}`;
     params += `,playback_id=${key}`;
-    params += ',vendor=verbio';
+    params += ',vendor=murf';
     params += `,voice=${voice}`;
+    if (model_id) params += `,model_id=${model_id}`;
+    if (language) params += `,language=${language}`;
+    if (api_uri) params += `,api_uri=${api_uri}`;
+    if (opts.style) params += `,style=${opts.style}`;
+    if (opts.rate !== undefined && opts.rate !== null) params += `,rate=${opts.rate}`;
+    if (opts.pitch !== undefined && opts.pitch !== null) params += `,pitch=${opts.pitch}`;
+    if (opts.variation !== undefined && opts.variation !== null) params += `,variation=${opts.variation}`;
     params += `,write_cache_file=${disableTtsCache ? 0 : 1}`;
     params += '}';
 
     return {
-      filePath: `say:${params}${text.replace(/\n/g, ' ')}`,
+      filePath: `say:${params}${text.replace(/\n/g, ' ').replace(/\r/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',
+    const sampleRate = 8000;
+    /* no Accept header: murf returns 406 if it doesn't match; the response
+       container is selected by the `format` field in the body instead */
+    const post = bent(api_uri || 'https://global.api.murf.ai', 'POST', 'buffer', {
+      'api-key': api_key,
       'Content-Type': 'application/json'
     });
-    const audioContent = await post('/api/v1/synthesize', {
+    /* murf REST schema is documented loosely; field names follow the SDK params
+       (voice_id/model/format/sample_rate) plus the websocket voice fields. */
+    const audioContent = await post('/v1/speech/stream', {
+      text,
       voice_id: voice,
-      output_sample_rate: '8k',
-      output_encoding: 'pcm16',
-      text
+      ...(model_id && {model: model_id}),
+      ...(language && {locale: language}),
+      ...(opts.style && {style: opts.style}),
+      ...(opts.rate !== undefined && opts.rate !== null && {rate: opts.rate}),
+      ...(opts.pitch !== undefined && opts.pitch !== null && {pitch: opts.pitch}),
+      ...(opts.variation !== undefined && opts.variation !== null && {variation: opts.variation}),
+      format: 'WAV',
+      sample_rate: sampleRate,
+      channel_type: 'MONO'
     });
     return {
       audioContent,
-      extension: 'r8',
-      sampleRate: 8000
+      extension: 'wav',
+      sampleRate
     };
   } catch (err) {
-    logger.info({err}, 'synth Verbio returned error');
-    stats.increment('tts.count', ['vendor:verbio', 'accepted:no']);
+    logger.info({err}, 'synth murf returned error');
+    stats.increment('tts.count', ['vendor:murf', 'accepted:no']);
     throw err;
   }
 };
-
 const synthWhisper = async(logger, {credentials, stats, voice, key, text, instructions,
   renderForCaching, disableTtsStreaming, disableTtsCache}) => {
   const {api_key, model_id, baseURL, timeout, speed} = credentials;

package/lib/utils.js

@@ -1,20 +1,7 @@
 const crypto = require('crypto');
-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 NUANCE_AUTH_ENDPOINT = 'tts.api.nuance.com:443';
 const grpc = require('@grpc/grpc-js');
-const formurlencoded = require('form-urlencoded');
-const { TMP_FOLDER, HTTP_TIMEOUT } = require('./config');
-
-const debug = require('debug')('jambonz:realtimedb-helpers');
-/**
- * Future TODO: cache recently used connections to providers
- * to avoid connection overhead during a call.
- * Will need to periodically age them out to avoid memory leaks.
- */
-//const nuanceClientMap = new Map();
+const { TMP_FOLDER } = require('./config');
 
 function makeSynthKey({
   account_sid = '',
@@ -45,90 +32,12 @@ const noopLogger = {
   error: () => {}
 };
 
-const toBase64 = (str) => Buffer.from(str || '', 'utf8').toString('base64');
-
-function makeBasicAuthHeader(username, password) {
-  if (!username || !password) return {};
-  const creds = `${encodeURIComponent(username)}:${password || ''}`;
-  const header = `Basic ${toBase64(creds)}`;
-  return {Authorization: header};
-}
-
 function makeAwsKey(awsAccessKeyId) {
   const hash = crypto.createHash('sha1');
   hash.update(awsAccessKeyId);
   return `aws:${hash.digest('hex')}`;
 }
 
-function makePlayhtKey(apiKey) {
-  const hash = crypto.createHash('sha1');
-  hash.update(apiKey);
-  return `playht:${hash.digest('hex')}`;
-}
-function makeVerbioKey(client_id) {
-  const hash = crypto.createHash('sha1');
-  hash.update(client_id);
-  return `verbio:${hash.digest('hex')}`;
-}
-
-function makeNuanceKey(clientId, secret, scope) {
-  const hash = crypto.createHash('sha1');
-  hash.update(`${clientId}:${secret}:${scope}`);
-  return `nuance:${hash.digest('hex')}`;
-}
-
-const getNuanceAccessToken = async(clientId, secret, scope = 'asr tts') => {
-  const payload = {
-    grant_type: 'client_credentials',
-    scope
-  };
-  const auth = makeBasicAuthHeader(clientId, secret);
-  const {statusCode, headers, body} =  await pool.request({
-    path: '/oauth2/token',
-    method: 'POST',
-    headers: {
-      ...auth,
-      'Content-Type': 'application/x-www-form-urlencoded'
-    },
-    body: formurlencoded(payload),
-    timeout: HTTP_TIMEOUT,
-    followRedirects: false
-  });
-
-  if (200 !== statusCode) {
-    debug({statusCode, headers, body: body.text()}, 'error fetching access token from Nuance');
-    const err = new Error();
-    err.statusCode = statusCode;
-    throw err;
-  }
-  const json = await body.json();
-  return json.access_token;
-};
-
-const createKryptonClient = async(uri) => {
-  const client = new SynthesizerClient(uri, grpc.credentials.createInsecure());
-  return client;
-};
-
-const createNuanceClient = async(access_token) => {
-
-  //if (nuanceClientMap.has(access_token)) return nuanceClientMap.get(access_token);
-
-  const generateMetadata = (params, callback) => {
-    var metadata = new grpc.Metadata();
-    metadata.add('authorization', `Bearer ${access_token}`);
-    callback(null, metadata);
-  };
-
-  const sslCreds = grpc.credentials.createSsl();
-  const authCreds = grpc.credentials.createFromMetadataGenerator(generateMetadata);
-  const combined_creds = grpc.credentials.combineChannelCredentials(sslCreds, authCreds);
-  const client = new SynthesizerClient(NUANCE_AUTH_ENDPOINT, combined_creds);
-
-  //if (process.env.NUANCE_CACHE_TTS_CONNECTIONS) nuanceClientMap.set(access_token, client);
-  return client;
-};
-
 const createRivaClient = async(rivaUri) => {
   const client = new RivaSpeechSynthesisClient(rivaUri, grpc.credentials.createInsecure());
   return client;
@@ -136,17 +45,8 @@ const createRivaClient = async(rivaUri) => {
 
 module.exports = {
   makeSynthKey,
-  makeNuanceKey,
-
-  makePlayhtKey,
   makeAwsKey,
-  makeVerbioKey,
-  getNuanceAccessToken,
-  createNuanceClient,
-  createKryptonClient,
   createRivaClient,
-  makeBasicAuthHeader,
-  NUANCE_AUTH_ENDPOINT,
   noopLogger,
   makeFilePath
 };