@jambonz/speech-utils 1.0.6 → 1.0.7

package/lib/synth-audio.js

@@ -80,7 +80,7 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
   logger = logger || noopLogger;
 
   assert.ok(['google', 'aws', 'polly', 'microsoft', 'wellsaid', 'nvidia', 'elevenlabs',
-    'whisper', 'deepgram', 'rimelabs', 'cartesia', 'inworld', 'resemble'].includes(vendor) ||
+    'whisper', 'deepgram', 'rimelabs', 'cartesia', 'inworld', 'resemble', 'murf'].includes(vendor) ||
   vendor.startsWith('custom'),
   `synthAudio supported vendors are google, aws, microsoft, nvidia and wellsaid ..etc, not ${vendor}`);
   if ('google' === vendor) {
@@ -127,6 +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');
@@ -211,6 +214,11 @@ 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,
@@ -969,6 +977,72 @@ const synthRimelabs = async(logger, {
     throw err;
   }
 };
+
+const synthMurf = async(logger, {
+  credentials, options, stats, language, voice, key, text, renderForCaching, disableTtsStreaming, disableTtsCache
+}) => {
+  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 += `api_key=${api_key}`;
+    params += `,playback_id=${key}`;
+    params += ',vendor=murf';
+    params += `,voice=${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, ' ').replace(/\r/g, ' ')}`,
+      servedFromCache: false,
+      rtt: 0
+    };
+  }
+
+  try {
+    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'
+    });
+    /* 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,
+      ...(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: 'wav',
+      sampleRate
+    };
+  } catch (err) {
+    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/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jambonz/speech-utils",
-  "version": "1.0.6",
+  "version": "1.0.7",
   "description": "TTS-related speech utilities for jambonz",
   "main": "index.js",
   "author": "Dave Horton",