@jambonz/speech-utils 0.2.24 → 0.2.26

package/.github/workflows/ci.yml

@@ -11,7 +11,7 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-node@v4
         with:
-          node-version: lts/*
+          node-version: '20'
       - run: npm install
       - name: Install Docker Compose
         run: |

package/lib/synth-audio.js

@@ -877,7 +877,7 @@ const synthCustomVendor = async(logger, {credentials, stats, language, voice,
 const synthElevenlabs = async(logger, {
   credentials, options, stats, voice, key, text, renderForCaching, disableTtsStreaming, disableTtsCache
 }) => {
-  const {api_key, model_id, options: credOpts} = credentials;
+  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 */
@@ -889,6 +889,7 @@ const synthElevenlabs = async(logger, {
     params += `,voice=${voice}`;
     params += `,model_id=${model_id}`;
     params += `,write_cache_file=${disableTtsCache ? 0 : 1}`;
+    if (api_uri) params += `,api_uri=${api_uri}`;
     if (opts.optimize_streaming_latency !== null && opts.optimize_streaming_latency !== undefined) {
       params += `,optimize_streaming_latency=${opts.optimize_streaming_latency}`;
     }
@@ -914,7 +915,7 @@ const synthElevenlabs = async(logger, {
   const optimize_streaming_latency = opts.optimize_streaming_latency ?
     `?optimize_streaming_latency=${opts.optimize_streaming_latency}` : '';
   try {
-    const post = bent('https://api.elevenlabs.io', 'POST', 'buffer', {
+    const post = bent(`https://${api_uri}`, 'POST', 'buffer', {
       'xi-api-key': api_key,
       'Accept': 'audio/mpeg',
       'Content-Type': 'application/json'
@@ -1315,6 +1316,7 @@ const synthCartesia = async(logger, {
     if (embedding) params += `,embedding=${embedding}`;
     if (opts.speed) params += `,speed=${opts.speed}`;
     if (opts.emotion) params += `,emotion=${opts.emotion}`;
+    if (opts.volume) params += `,volume=${opts.volume}`;
     params += '}';
 
     return {
@@ -1340,13 +1342,20 @@ const synthCartesia = async(logger, {
             id: voice
           }
         ),
-        ...(opts.speed || opts.emotion && {
+        ...(model_id === 'sonic-2' && (opts.speed || opts.emotion) && {
           experimentalControls: {
             ...(opts.speed !== null && opts.speed !== undefined && {speed: opts.speed}),
-            ...(opts.emotion && {emotion: opts.emotion}),
+            ...(opts.emotion && {emotion: [opts.emotion]}),
           }
-        })
+        }),
       },
+      ...(model_id === 'sonic-3' && (opts.speed || opts.emotion || opts.volume) && {
+        generationConfig: {
+          ...(opts.volume !== null && opts.volume !== undefined && {volume: opts.volume}),
+          ...(opts.speed !== null && opts.speed !== undefined && {speed: opts.speed}),
+          ...(opts.emotion !== null && opts.emotion !== undefined && {emotion: opts.emotion}),
+        }
+      }),
       language: language,
       outputFormat: {
         container: 'mp3',

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jambonz/speech-utils",
-  "version": "0.2.24",
+  "version": "0.2.26",
   "description": "TTS-related speech utilities for jambonz",
   "main": "index.js",
   "author": "Dave Horton",
@@ -29,7 +29,7 @@
     "23": "^0.0.0",
     "@aws-sdk/client-polly": "^3.496.0",
     "@aws-sdk/client-sts": "^3.496.0",
-    "@cartesia/cartesia-js": "^2.1.0",
+    "@cartesia/cartesia-js": "^2.2.7",
     "@google-cloud/text-to-speech": "^5.5.0",
     "@grpc/grpc-js": "^1.9.14",
     "@jambonz/realtimedb-helpers": "^0.8.7",