@jambonz/speech-utils 1.0.14 → 1.0.16

package/lib/synth-audio.js

@@ -941,8 +941,9 @@ const synthInworld = async(logger, {
     params += `,voice=${voice}`;
     params += `,write_cache_file=${disableTtsCache ? 0 : 1}`;
     if (opts.temperature) params += `,temperature=${opts.temperature}`;
-    if (opts.audioConfig?.pitch) params += `,pitch=${opts.pitch}`;
-    if (opts.audioConfig?.speakingRate) params += `,speakingRate=${opts.speakingRate}`;
+    /* pitch and speakingRate are nested under audioConfig, matching Inworld's API */
+    if (opts.audioConfig?.pitch) params += `,pitch=${opts.audioConfig.pitch}`;
+    if (opts.audioConfig?.speakingRate) params += `,speakingRate=${opts.audioConfig.speakingRate}`;
     params += '}';
 
     return {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jambonz/speech-utils",
-  "version": "1.0.14",
+  "version": "1.0.16",
   "description": "TTS-related speech utilities for jambonz",
   "main": "index.js",
   "author": "Dave Horton",
@@ -25,7 +25,6 @@
   },
   "homepage": "https://github.com/jambonz/speech-utils#readme",
   "dependencies": {
-    "23": "^0.0.0",
     "@aws-sdk/client-polly": "^3.496.0",
     "@aws-sdk/client-sts": "^3.496.0",
     "@cartesia/cartesia-js": "^2.2.7",

package/test/synth.js

@@ -1147,6 +1147,69 @@ test('inworld speech synth', async(t) => {
   client.quit();
 });
 
+test('inworld streaming say: params', async(t) => {
+  /* This test asserts the streaming say: path, so it must run with streaming
+     enabled. The Google non-streaming test above sets
+     JAMBONES_DISABLE_TTS_STREAMING and, on its no-credentials skip path,
+     deletes the env var WITHOUT clearing the require cache — so lib/config can
+     still be holding 'true' by the time we get here. Re-require to be
+     independent of what ran before us.
+   */
+  delete process.env.JAMBONES_DISABLE_TTS_STREAMING;
+  delete require.cache[require.resolve('../lib/config')];
+  delete require.cache[require.resolve('../lib/synth-audio')];
+  delete require.cache[require.resolve('..')];
+
+  const fn = require('..');
+  const {synthAudio, client} = fn(opts, logger);
+
+  if (!process.env.INWORLD_API_KEY) {
+    t.pass('skipping inworld streaming say: param tests since INWORLD_API_KEY is not provided');
+    client.quit();
+    return t.end();
+  }
+
+  try {
+    let result = await synthAudio(stats, {
+      vendor: 'inworld',
+      credentials: {api_key: process.env.INWORLD_API_KEY, model_id: 'inworld-tts-1.5-mini'},
+      language: 'en',
+      voice: 'Ashley',
+      text: 'This is a test of inworld streaming.',
+      options: {temperature: 0.9, audioConfig: {pitch: 2.5, speakingRate: 1.2}},
+      disableTtsCache: true
+    });
+    t.ok(result.filePath.startsWith('say:'), 'inworld returns streaming say: path');
+    t.ok(result.filePath.includes('vendor=inworld'), 'streaming path contains vendor=inworld');
+    t.ok(result.filePath.includes('voice=Ashley'), 'streaming path contains voice');
+    t.ok(result.filePath.includes('model_id=inworld-tts-1.5-mini'), 'streaming path contains model_id');
+    t.ok(result.filePath.includes('temperature=0.9'), 'streaming path contains temperature');
+    /* pitch and speakingRate are nested under audioConfig; they used to be read
+       from the top level and emitted as "undefined"
+     */
+    t.ok(result.filePath.includes('speakingRate=1.2'), 'audioConfig.speakingRate reaches the say: params');
+    t.ok(result.filePath.includes('pitch=2.5'), 'audioConfig.pitch reaches the say: params');
+    t.ok(!result.filePath.includes('undefined'), 'no undefined values in the say: params');
+
+    /* options omitted entirely: no stray keys */
+    result = await synthAudio(stats, {
+      vendor: 'inworld',
+      credentials: {api_key: process.env.INWORLD_API_KEY, model_id: 'inworld-tts-1.5-mini'},
+      language: 'en',
+      voice: 'Ashley',
+      text: 'This is a test of inworld streaming.',
+      disableTtsCache: true
+    });
+    t.ok(!result.filePath.includes('speakingRate='), 'speakingRate omitted when unset');
+    t.ok(!result.filePath.includes('pitch='), 'pitch omitted when unset');
+    t.ok(!result.filePath.includes('undefined'), 'no undefined values when options are omitted');
+  } catch (err) {
+    console.error(JSON.stringify(err));
+    t.end(err);
+  }
+  client.quit();
+});
+
 test('resemble speech synth', async(t) => {
   const fn = require('..');
   const {synthAudio, client} = fn(opts, logger);