@jambonz/speech-utils 1.0.3 → 1.0.6

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
 };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jambonz/speech-utils",
-  "version": "1.0.3",
+  "version": "1.0.6",
   "description": "TTS-related speech utilities for jambonz",
   "main": "index.js",
   "author": "Dave Horton",
@@ -13,7 +13,6 @@
     "coverage": "nyc --reporter html --report-dir ./coverage npm run test",
     "jslint": "eslint index.js lib",
     "jslint:fix": "npm run jslint --fix",
-    "build": "./build_stubs.sh",
     "prepare": "husky"
   },
   "repository": {
@@ -35,7 +34,6 @@
     "@jambonz/realtimedb-helpers": "^0.8.7",
     "bent": "^7.3.12",
     "debug": "^4.3.4",
-    "form-urlencoded": "^6.1.4",
     "google-protobuf": "^3.21.2",
     "microsoft-cognitiveservices-speech-sdk": "1.38.0",
     "openai": "^4.98.0",

package/test/index.js

@@ -3,5 +3,4 @@ require('./synth');
 require('./list-voices');
 require('./aws');
 
-require('./nuance');
 require('./docker_stop');

package/test/list-voices.js

@@ -12,99 +12,6 @@ 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('Nuance hosted tests', async(t) => {
-  const fn = require('..');
-  const {client, getTtsVoices} = fn(opts, logger);
-
-  if (!process.env.NUANCE_CLIENT_ID || !process.env.NUANCE_SECRET ) {
-      t.pass('skipping Nuance hosted test since no Nuance client_id and secret provided');
-      t.end();
-      client.quit();
-      return;
-  }
-  try {
-    const opts = {
-      vendor: 'nuance',
-      credentials: {
-        client_id: process.env.NUANCE_CLIENT_ID,
-        secret: process.env.NUANCE_SECRET
-      }
-    };
-    let voices = await getTtsVoices(opts);
-    t.ok(voices.length > 0 && voices[0].language, 
-      `GetVoices: successfully retrieved ${voices.length} voices from Nuance`);
-
-    await client.flushall();
-
-    t.end();
-
-  }
-  catch (err) {
-    console.error(err);
-    t.end(err);
-  }
-  client.quit();
-});
-
-test('Nuance on-prem tests', async(t) => {
-  const fn = require('..');
-  const {client, getTtsVoices} = fn(opts, logger);
-
-  if (!process.env.NUANCE_TTS_URI ) {
-      t.pass('skipping Nuance on-prem test since no Nuance uri provided');
-      t.end();
-      client.quit();
-      return;
-  }
-  try {
-    const opts = {
-      vendor: 'nuance',
-      credentials: {
-        nuance_tts_uri: process.env.NUANCE_TTS_URI
-      }
-    };
-    let voices = await getTtsVoices(opts);
-    t.ok(voices.length > 0 && voices[0].language, 
-      `GetVoices: successfully retrieved ${voices.length} voices from Nuance`);
-
-    await client.flushall();
-
-    t.end();
-
-  }
-  catch (err) {
-    console.error(err);
-    t.end(err);
-  }
-  client.quit();
-});
-
 test('Google tests', async(t) => {
   const fn = require('..');
   const {client, getTtsVoices} = fn(opts, logger);

package/test/synth.js

@@ -759,82 +759,6 @@ test('Azure custom voice speech synth tests', async(t) => {
   client.quit();
 });
 
-test('Nuance hosted speech synth tests', async(t) => {
-  const fn = require('..');
-  const {synthAudio, client} = fn(opts, logger);
-
-  if (!process.env.NUANCE_CLIENT_ID || !process.env.NUANCE_SECRET) {
-    t.pass('skipping Nuance speech synth tests since NUANCE_CLIENT_ID or NUANCE_SECRET not provided');
-    return t.end();
-  }
-  try {
-    let opts = await synthAudio(stats, {
-      vendor: 'nuance',
-      credentials: {
-        client_id: process.env.NUANCE_CLIENT_ID,
-        secret: process.env.NUANCE_SECRET,
-      },
-      language: 'en-US',
-      voice: 'Evan',
-      text: 'This is a test.  This is only a test',
-    });
-    t.ok(!opts.servedFromCache, `successfully synthesized nuance audio to ${opts.filePath}`);
-
-    opts = await synthAudio(stats, {
-      vendor: 'nuance',
-      credentials: {
-        client_id: process.env.NUANCE_CLIENT_ID,
-        secret: process.env.NUANCE_SECRET,
-      },
-      language: 'en-US',
-      voice: 'Evan',
-      text: 'This is a test.  This is only a test',
-    });
-    t.ok(opts.servedFromCache, `successfully retrieved nuance audio from cache ${opts.filePath}`);
-  } catch (err) {
-    console.error(err);
-    t.end(err);
-  }
-  client.quit();
-});
-
-test('Nuance on-prem speech synth tests', async(t) => {
-  const fn = require('..');
-  const {synthAudio, client} = fn(opts, logger);
-
-  if (!process.env.NUANCE_TTS_URI) {
-    t.pass('skipping Nuance on prem speech synth tests since NUANCE_TTS_URI not provided');
-    return t.end();
-  }
-  try {
-    let opts = await synthAudio(stats, {
-      vendor: 'nuance',
-      credentials: {
-        nuance_tts_uri: process.env.NUANCE_TTS_URI
-      },
-      language: 'en-US',
-      voice: 'Evan',
-      text: 'This is a test of on-prem.  This is only a test',
-    });
-    t.ok(!opts.servedFromCache, `successfully synthesized nuance audio to ${opts.filePath}`);
-
-    opts = await synthAudio(stats, {
-      vendor: 'nuance',
-      credentials: {
-        nuance_tts_uri: process.env.NUANCE_TTS_URI
-      },
-      language: 'en-US',
-      voice: 'Evan',
-      text: 'This is a test of on-prem.  This is only a test',
-    });
-    t.ok(opts.servedFromCache, `successfully retrieved nuance audio from cache ${opts.filePath}`);
-  } catch (err) {
-    console.error(err);
-    t.end(err);
-  }
-  client.quit();
-});
-
 test('Nvidia speech synth tests', async(t) => {
   const fn = require('..');
   const {synthAudio, client} = fn(opts, logger);
@@ -975,55 +899,6 @@ test('Elevenlabs speech synth tests', async(t) => {
   client.quit();
 });
 
-const testPlayHT = async(t, voice_engine) => {
-  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! ' + Date.now();
-  try {
-    const opts = await synthAudio(stats, {
-      vendor: 'playht',
-      credentials: {
-        api_key: process.env.PLAYHT_API_KEY,
-        user_id: process.env.PLAYHT_USER_ID,
-        voice_engine,
-        options: JSON.stringify({
-          quality: 'medium',
-          speed: 1,
-          seed: 1,
-          temperature: 1,
-          emotion: 'female_happy',
-          voice_guidance: 3,
-          style_guidance: 20,
-          text_guidance: 1,
-        })
-      },
-      language: 'english',
-      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('PlayHT speech synth tests', async(t) => {
-  await testPlayHT(t, 'PlayHT2.0-turbo');
-});
-
-test('PlayHT3.0 speech synth tests', async(t) => {
-  await testPlayHT(t, 'Play3.0');
-});
-
 test('Cartesia speech synth tests', async(t) => {
   const fn = require('..');
   const {synthAudio, client} = fn(opts, logger);
@@ -1215,39 +1090,6 @@ test('whisper speech synth tests', async(t) => {
   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}`);
-
-  } catch (err) {
-    console.error(JSON.stringify(err));
-    t.end(err);
-  }
-  client.quit();
-})
-
 test('Deepgram speech synth tests', async(t) => {
   const fn = require('..');
   const {synthAudio, client} = fn(opts, logger);

package/build_stubs.sh

@@ -1,11 +0,0 @@
-#!/bin/sh
-
-mkdir -p stubs/nuance
-
-for FILE in ./protos/nuance/*; do 
-  grpc_tools_node_protoc   \
-  --js_out=import_style=commonjs,binary:./stubs/nuance \
-  --grpc_out=grpc_js:./stubs/nuance \
-  --proto_path=./protos/nuance  \
-  $FILE
-done

package/lib/get-nuance-access-token.js

@@ -1,49 +0,0 @@
-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('./config');
-const debug = require('debug')('jambonz:realtimedb-helpers');
-
-async function getNuanceAccessToken(client, logger, clientId, secret, scope) {
-  logger = logger || noopLogger;
-  try {
-    const key = makeNuanceKey(clientId, secret, scope);
-    const access_token = await client.get(key);
-    if (access_token) return {access_token, servedFromCache: true};
-
-    /* access token not found in cache, so fetch it from Nuance */
-    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) {
-      logger.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();
-    await client.set(key, json.access_token, 'EX', json.expires_in - 30);
-    return {...json, servedFromCache: false};
-  } catch (err) {
-    debug(err, `getNuanceAccessToken: Error retrieving Nuance access token for client_id ${clientId}`);
-    logger.error(err, `getNuanceAccessToken: Error retrieving Nuance access token for client_id ${clientId}`);
-    throw err;
-  }
-}
-
-module.exports = getNuanceAccessToken;

package/lib/get-verbio-token.js

@@ -1,51 +0,0 @@
-const {Pool} = require('undici');
-const { noopLogger, makeVerbioKey } = require('./utils');
-const { HTTP_TIMEOUT } = require('./config');
-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;