@jambonz/speech-utils 0.2.30 → 1.0.3

package/.github/workflows/ci.yml

@@ -13,11 +13,6 @@ jobs:
         with:
           node-version: '20'
       - run: npm install
-      - name: Install Docker Compose
-        run: |
-          sudo curl -L "https://github.com/docker/compose/releases/download/1.29.2/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose
-          sudo chmod +x /usr/local/bin/docker-compose
-          docker-compose --version
       - run: npm run jslint
       - run: sudo apt update && sudo apt install -y squid
       - run: sudo cp test/squid.conf /etc/squid/squid.conf
@@ -28,9 +23,7 @@ jobs:
           AWS_REGION: ${{ secrets.AWS_REGION }}
           AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
           GCP_JSON_KEY: ${{ secrets.GCP_JSON_KEY }}
-          IBM_API_KEY: ${{ secrets.IBM_API_KEY }}
-          IBM_TTS_API_KEY: ${{ secrets.IBM_TTS_API_KEY }}
-          IBM_TTS_REGION: ${{ secrets.IBM_TTS_REGION }}
+
           MICROSOFT_API_KEY: ${{ secrets.MICROSOFT_API_KEY }}
           MICROSOFT_REGION: ${{ secrets.MICROSOFT_REGION }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}

package/index.js

@@ -16,7 +16,7 @@ module.exports = (opts, 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, createHash, retrieveHash, logger),
   };

package/lib/get-tts-voices.js

@@ -3,8 +3,6 @@ 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');
@@ -12,21 +10,6 @@ const {Pool} = require('undici');
 const { HTTP_TIMEOUT } = require('./config');
 const verbioVoicePool = new Pool('https://us.rest.speechcenter.verbio.com');
 
-const getIbmVoices = async(client, logger, credentials) => {
-  const {tts_region, tts_api_key} = credentials;
-  console.log(`region: ${tts_region}, api_key: ${tts_api_key}`);
-
-  const textToSpeech = new TextToSpeechV1({
-    authenticator: new IamAuthenticator({
-      apikey: tts_api_key,
-    }),
-    serviceUrl: `https://api.${tts_region}.text-to-speech.watson.cloud.ibm.com`
-  });
-
-  const voices = await textToSpeech.listVoices();
-  return voices;
-};
-
 const getNuanceVoices = async(client, logger, credentials) => {
   const {client_id: clientId, secret: secret, nuance_tts_uri} = credentials;
 
@@ -165,14 +148,12 @@ const getVerbioVoices = async(client, logger, credentials) => {
 async function getTtsVoices(client, createHash, retrieveHash, logger, {vendor, credentials}) {
   logger = logger || noopLogger;
 
-  assert.ok(['nuance', 'ibm', 'google', 'aws', 'polly', 'verbio'].includes(vendor),
+  assert.ok(['nuance', 'google', 'aws', 'polly', 'verbio'].includes(vendor),
     `getTtsVoices not supported for vendor ${vendor}`);
 
   switch (vendor) {
     case 'nuance':
       return getNuanceVoices(client, logger, credentials);
-    case 'ibm':
-      return getIbmVoices(client, logger, credentials);
     case 'google':
       return getGoogleVoices(client, logger, credentials);
     case 'aws':

package/lib/synth-audio.js

@@ -6,8 +6,7 @@ const { PollyClient, SynthesizeSpeechCommand } = require('@aws-sdk/client-polly'
 const { CartesiaClient } = require('@cartesia/cartesia-js');
 
 const sdk = require('microsoft-cognitiveservices-speech-sdk');
-const TextToSpeechV1 = require('ibm-watson/text-to-speech/v1');
-const { IamAuthenticator } = require('ibm-watson/auth');
+
 const {
   ResultReason,
   SpeechConfig,
@@ -96,7 +95,7 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
   let rtt;
   logger = logger || noopLogger;
 
-  assert.ok(['google', 'aws', 'polly', 'microsoft', 'wellsaid', 'nuance', 'nvidia', 'ibm', 'elevenlabs',
+  assert.ok(['google', 'aws', 'polly', 'microsoft', 'wellsaid', 'nuance', 'nvidia', 'elevenlabs',
     'whisper', 'deepgram', 'playht', 'rimelabs', 'verbio', 'cartesia', 'inworld', 'resemble'].includes(vendor) ||
   vendor.startsWith('custom'),
   `synthAudio supported vendors are google, aws, microsoft, nuance, nvidia and wellsaid ..etc, not ${vendor}`);
@@ -122,11 +121,6 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
     assert.ok(language, 'synthAudio requires language when nvidia is used');
     assert.ok(credentials.riva_server_uri, 'synthAudio requires riva_server_uri in credentials when nvidia is used');
   }
-  else if ('ibm' === vendor) {
-    assert.ok(voice, 'synthAudio requires voice when ibm is used');
-    assert.ok(credentials.tts_region, 'synthAudio requires tts_region in credentials when ibm watson is used');
-    assert.ok(credentials.tts_api_key, 'synthAudio requires tts_api_key in credentials when nuance is used');
-  }
   else if ('wellsaid' === vendor) {
     language = 'en-US'; // WellSaid only supports English atm
     assert.ok(voice, 'synthAudio requires voice when wellsaid is used');
@@ -230,9 +224,6 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
         audioData = await synthNvidia(client, logger, {credentials, stats, language, voice, model, key, text,
           renderForCaching, disableTtsStreaming, disableTtsCache});
         break;
-      case 'ibm':
-        audioData = await synthIbm(logger, {credentials, stats, voice, key, text});
-        break;
       case 'wellsaid':
         audioData = await synthWellSaid(logger, {credentials, stats, language, voice, key, text});
         break;
@@ -535,39 +526,6 @@ const synthGoogle = async(logger, {
   }
 };
 
-const synthIbm = async(logger, {credentials, stats, voice, text}) => {
-  const {tts_api_key, tts_region} = credentials;
-  const params = {
-    text,
-    voice,
-    accept: 'audio/mp3'
-  };
-
-  try {
-    const textToSpeech = new TextToSpeechV1({
-      authenticator: new IamAuthenticator({
-        apikey: tts_api_key,
-      }),
-      serviceUrl: `https://api.${tts_region}.text-to-speech.watson.cloud.ibm.com`
-    });
-
-    const r = await textToSpeech.synthesize(params);
-    const chunks = [];
-    for await (const chunk of r.result) {
-      chunks.push(chunk);
-    }
-    return {
-      audioContent: Buffer.concat(chunks),
-      extension: 'mp3',
-      sampleRate: 8000
-    };
-  } catch (err) {
-    logger.info({err, params}, 'synthAudio: Error synthesizing speech using ibm');
-    stats.increment('tts.count', ['vendor:ibm', 'accepted:no']);
-    throw new Error(err.statusText || err.message);
-  }
-};
-
 async function _synthOnPremMicrosoft(logger, {
   credentials,
   language,
@@ -969,7 +927,7 @@ const synthElevenlabs = async(logger, {
   const optimize_streaming_latency = opts.optimize_streaming_latency ?
     `?optimize_streaming_latency=${opts.optimize_streaming_latency}` : '';
   try {
-    const post = bent(`https://${api_uri}`, 'POST', 'buffer', {
+    const post = bent(`https://${api_uri || 'api.elevenlabs.io'}`, 'POST', 'buffer', {
       'xi-api-key': api_key,
       'Accept': 'audio/mpeg',
       'Content-Type': 'application/json'
@@ -1178,6 +1136,8 @@ const synthRimelabs = async(logger, {
     if (opts.repetition_penalty) params += `,repetition_penalty=${opts.repetition_penalty}`;
     if (opts.top_p) params += `,top_p=${opts.top_p}`;
     if (opts.max_tokens) params += `,max_tokens=${opts.max_tokens}`;
+    // Coda model parameters
+    if (opts.timeScaleFactor) params += `,time_scale_factor=${opts.timeScaleFactor}`;
     params += '}';
 
     return {

package/lib/utils.js

@@ -54,12 +54,6 @@ function makeBasicAuthHeader(username, password) {
   return {Authorization: header};
 }
 
-function makeIbmKey(apiKey) {
-  const hash = crypto.createHash('sha1');
-  hash.update(apiKey);
-  return `ibm:${hash.digest('hex')}`;
-}
-
 function makeAwsKey(awsAccessKeyId) {
   const hash = crypto.createHash('sha1');
   hash.update(awsAccessKeyId);
@@ -143,7 +137,7 @@ const createRivaClient = async(rivaUri) => {
 module.exports = {
   makeSynthKey,
   makeNuanceKey,
-  makeIbmKey,
+
   makePlayhtKey,
   makeAwsKey,
   makeVerbioKey,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jambonz/speech-utils",
-  "version": "0.2.30",
+  "version": "1.0.3",
   "description": "TTS-related speech utilities for jambonz",
   "main": "index.js",
   "author": "Dave Horton",
@@ -37,7 +37,6 @@
     "debug": "^4.3.4",
     "form-urlencoded": "^6.1.4",
     "google-protobuf": "^3.21.2",
-    "ibm-watson": "^11.0.0",
     "microsoft-cognitiveservices-speech-sdk": "1.38.0",
     "openai": "^4.98.0",
     "undici": "^7.5.0"

package/test/docker_start.js

@@ -2,7 +2,7 @@ const test = require('tape').test ;
 const exec = require('child_process').exec ;
 
 test('starting docker network..', (t) => {
-  exec(`docker-compose -f ${__dirname}/docker-compose-testbed.yaml up -d`, (err, stdout, stderr) => {
+  exec(`docker compose -f ${__dirname}/docker-compose-testbed.yaml up -d`, (err, stdout, stderr) => {
     setTimeout(() => {
       t.end(err);
     }, 2000);

package/test/docker_stop.js

@@ -3,7 +3,7 @@ const exec = require('child_process').exec ;
 
 test('stopping docker network..', (t) => {
   t.timeoutAfter(10000);
-  exec(`docker-compose -f ${__dirname}/docker-compose-testbed.yaml down`, (err, stdout, stderr) => {
+  exec(`docker compose -f ${__dirname}/docker-compose-testbed.yaml down`, (err, stdout, stderr) => {
     //console.log(`stderr: ${stderr}`);
     process.exit(0);
   });

package/test/index.js

@@ -2,6 +2,6 @@ require('./docker_start');
 require('./synth');
 require('./list-voices');
 require('./aws');
-require('./ibm');
+
 require('./nuance');
 require('./docker_stop');

package/test/list-voices.js

@@ -38,71 +38,6 @@ test('Verbio - get Access key and voices', async(t) => {
   client.quit();
 });
 
-test('IBM - create access key', async(t) => {
-  const fn = require('..');
-  const {client, getIbmAccessToken} = fn(opts, logger);
-
-  if (!process.env.IBM_API_KEY ) {
-      t.pass('skipping IBM test since no IBM api_key provided');
-      t.end();
-      client.quit();
-      return;
-  }
-  try {
-    let obj = await getIbmAccessToken(process.env.IBM_API_KEY);
-    //console.log({obj}, 'received access token from IBM');
-    t.ok(obj.access_token && !obj.servedFromCache, 'successfull received access token from IBM');
-
-    obj = await getIbmAccessToken(process.env.IBM_API_KEY);
-    //console.log({obj}, 'received access token from IBM - second request');
-    t.ok(obj.access_token && obj.servedFromCache, 'successfully received access token from cache');
- 
-    await client.flushall();
-    t.end();
-  }
-  catch (err) {
-    console.error(err);
-    t.end(err);
-  }
-  client.quit();
-});
-
-test('IBM - retrieve tts voices test', async(t) => {
-  const fn = require('..');
-  const {client, getTtsVoices} = fn(opts, logger);
-
-  if (!process.env.IBM_TTS_API_KEY || !process.env.IBM_TTS_REGION) {
-      t.pass('skipping IBM test since no IBM api_key and/or region provided');
-      t.end();
-      client.quit();
-      return;
-  }
-  try {
-    const opts = {
-      vendor: 'ibm',
-      credentials: {
-        tts_api_key: process.env.IBM_TTS_API_KEY,
-        tts_region: process.env.IBM_TTS_REGION
-      }
-    };
-    const obj = await getTtsVoices(opts);
-    const {voices} = obj.result;
-    //console.log(JSON.stringify(voices));
-    t.ok(voices.length > 0 && voices[0].language, 
-      `GetVoices: successfully retrieved ${voices.length} voices from IBM`);
- 
-    await client.flushall();
-
-    t.end();
-
-  }
-  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);

package/test/synth.js

@@ -872,46 +872,6 @@ test('Nvidia speech synth tests', async(t) => {
   client.quit();
 });
 
-test('IBM watson speech synth tests', async(t) => {
-  const fn = require('..');
-  const {synthAudio, client} = fn(opts, logger);
-
-  if (!process.env.IBM_TTS_API_KEY || !process.env.IBM_TTS_REGION) {
-    t.pass('skipping IBM Watson speech synth tests since IBM_TTS_API_KEY or IBM_TTS_API_KEY not provided');
-    return t.end();
-  }
-  const text = `<speak> Hi there and welcome to jambones! jambones is the <sub alias="seapass">CPaaS</sub> designed with the needs of communication service providers in mind. This is an example of simple text-to-speech, but there is so much more you can do. Try us out!</speak>`;
-  try {
-    let opts = await synthAudio(stats, {
-      vendor: 'ibm',
-      credentials: {
-        tts_api_key: process.env.IBM_TTS_API_KEY,
-        tts_region: process.env.IBM_TTS_REGION,
-      },
-      language: 'en-US',
-      voice: 'en-US_AllisonV2Voice',
-      text,
-    });
-    t.ok(!opts.servedFromCache, `successfully synthesized ibm audio to ${opts.filePath}`);
-
-    opts = await synthAudio(stats, {
-      vendor: 'ibm',
-      credentials: {
-        tts_api_key: process.env.IBM_TTS_API_KEY,
-        tts_region: process.env.IBM_TTS_REGION,
-      },
-      language: 'en-US',
-      voice: 'en-US_AllisonV2Voice',
-      text,
-    });
-    t.ok(opts.servedFromCache, `successfully retrieved ibm audio from cache ${opts.filePath}`);
-  } catch (err) {
-    console.error(JSON.stringify(err));
-    t.end(err);
-  }
-  client.quit();
-});
-
 test('Custom Vendor speech synth tests', async(t) => {
   const fn = require('..');
   const {synthAudio, client} = fn(opts, logger);

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

@@ -1,48 +0,0 @@
-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('./config');
-const debug = require('debug')('jambonz:realtimedb-helpers');
-
-async function getIbmAccessToken(client, logger, apiKey) {
-  logger = logger || noopLogger;
-  try {
-    const key = makeIbmKey(apiKey);
-    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 Ibm */
-    const payload = {
-      grant_type: 'urn:ibm:params:oauth:grant-type:apikey',
-      apikey: apiKey
-    };
-    const {statusCode, headers, body} =  await pool.request({
-      path: '/identity/token',
-      method: 'POST',
-      headers: {
-        'Content-Type': 'application/x-www-form-urlencoded'
-      },
-      body: formurlencoded(payload),
-      timeout: HTTP_TIMEOUT,
-      followRedirects: false
-    });
-
-    if (200 !== statusCode) {
-      const json = await body.json();
-      logger.debug({statusCode, headers, body: json}, 'error fetching access token from Ibm');
-      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, 'getIbmAccessToken: Error retrieving Ibm access token');
-    logger.error(err, 'getIbmAccessToken: Error retrieving Ibm access token for client_id ${clientId}');
-    throw err;
-  }
-}
-
-module.exports = getIbmAccessToken;

package/test/ibm.js

@@ -1,78 +0,0 @@
-const test = require('tape').test ;
-const config = require('config');
-const opts = config.get('redis');
-const fs = require('fs');
-const logger = require('pino')({level: 'error'});
-process.on('unhandledRejection', (reason, p) => {
-  console.log('Unhandled Rejection at: Promise', p, 'reason:', reason);
-});
-
-const stats = {
-  increment: () => {},
-  histogram: () => {}
-};
-
-test('IBM - create access key', async(t) => {
-  const fn = require('..');
-  const {client, getIbmAccessToken} = fn(opts, logger);
-
-  if (!process.env.IBM_API_KEY ) {
-      t.pass('skipping IBM test since no IBM api_key provided');
-      t.end();
-      client.quit();
-      return;
-  }
-  try {
-    let obj = await getIbmAccessToken(process.env.IBM_API_KEY);
-    //console.log({obj}, 'received access token from IBM');
-    t.ok(obj.access_token && !obj.servedFromCache, 'successfull received access token from IBM');
-
-    obj = await getIbmAccessToken(process.env.IBM_API_KEY);
-    //console.log({obj}, 'received access token from IBM - second request');
-    t.ok(obj.access_token && obj.servedFromCache, 'successfully received access token from cache');
- 
-    await client.flushall();
-    t.end();
-  }
-  catch (err) {
-    console.error(err);
-    t.end(err);
-  }
-  client.quit();
-});
-
-test('IBM - retrieve tts voices test', async(t) => {
-  const fn = require('..');
-  const {client, getTtsVoices} = fn(opts, logger);
-
-  if (!process.env.IBM_TTS_API_KEY || !process.env.IBM_TTS_REGION) {
-      t.pass('skipping IBM test since no IBM api_key and/or region provided');
-      t.end();
-      client.quit();
-      return;
-  }
-  try {
-    const opts = {
-      vendor: 'ibm',
-      credentials: {
-        tts_api_key: process.env.IBM_TTS_API_KEY,
-        tts_region: process.env.IBM_TTS_REGION
-      }
-    };
-    const obj = await getTtsVoices(opts);
-    const {voices} = obj.result;
-    //console.log(JSON.stringify(voices));
-    t.ok(voices.length > 0 && voices[0].language, 
-      `GetVoices: successfully retrieved ${voices.length} voices from IBM`);
- 
-    await client.flushall();
-
-    t.end();
-
-  }
-  catch (err) {
-    console.error(err);
-    t.end(err);
-  }
-  client.quit();
-});