1.0.18

Adds synthFishaudio with both arms: the say: streaming url consumed by the
mediajam dialect, and a POST /v1/tts cache render. The render asks for raw pcm
at 8k and returns extension r8 because fish's wav output carries a placeholder
RIFF size, the same problem gradium has.

Fish is a voice-cloning vendor, so the voice is a reference_id; the sentinel
'default' means send none and use fish's own default voice.

Co-authored-by: Claude Opus 5 <noreply@anthropic.com>

CLAUDE.md

@@ -0,0 +1,84 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Overview
+
+`@jambonz/speech-utils` is a Node.js library providing TTS (Text-to-Speech) utilities for the jambonz CPaaS platform. It handles speech synthesis with caching through Redis and supports multiple TTS vendors.
+
+## Commands
+
+```bash
+# Run tests (requires Docker for Redis)
+npm test
+
+# Run linter
+npm run jslint
+
+# Auto-fix lint issues
+npm run jslint:fix
+
+# Generate coverage report
+npm run coverage
+```
+
+## Testing
+
+Tests use `tape` and require Redis. The test harness automatically starts/stops Redis via Docker Compose (`test/docker-compose-testbed.yaml`).
+
+Most tests are conditional based on environment variables for vendor credentials:
+- `GCP_FILE` or `GCP_JSON_KEY` - Google TTS
+- `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_REGION` - AWS Polly
+- `MICROSOFT_API_KEY`, `MICROSOFT_REGION` - Azure TTS
+- `ELEVENLABS_API_KEY`, `ELEVENLABS_VOICE_ID`, `ELEVENLABS_MODEL_ID` - ElevenLabs
+- `OPENAI_API_KEY` - OpenAI Whisper TTS
+- And others per vendor
+
+Redis config is in `config/test.json` (port 3379).
+
+## Architecture
+
+### Entry Point
+
+`index.js` exports a factory function that takes Redis options and a logger, returning an object with these methods:
+- `synthAudio` - Main synthesis function
+- `getTtsVoices` - List available voices for a vendor
+- `purgeTtsCache` / `getTtsSize` / `addFileToCache` - Cache management
+- `getAwsAuthToken` - Token management
+
+### Core Module: `lib/synth-audio.js`
+
+The `synthAudio` function handles synthesis for all vendors. Key behaviors:
+1. **Cache check**: Generates SHA1 hash key from (vendor, language, voice, engine, model, text, instructions)
+2. **Streaming vs non-streaming**: When `JAMBONES_DISABLE_TTS_STREAMING` is not set and `renderForCaching=false`, returns `say:{params}text` format for FreeSWITCH streaming playback instead of generating files
+3. **Vendor dispatch**: Switch statement routes to vendor-specific synth functions (`synthGoogle`, `synthPolly`, `synthMicrosoft`, etc.)
+4. **Caching**: Stores audio as base64 JSON in Redis with configurable TTL (default 4 hours)
+
+### Supported Vendors
+
+google, aws/polly, microsoft/azure, nvidia (Riva), wellsaid, elevenlabs, cartesia, inworld, rimelabs, whisper (OpenAI), deepgram, resemble, custom:*
+
+### gRPC Stubs
+
+`stubs/riva/` contains generated protobuf/gRPC code for NVIDIA Riva.
+
+## Environment Variables
+
+Key configuration via env vars (see `lib/config.js`):
+- `JAMBONES_DISABLE_TTS_STREAMING` - Force non-streaming mode
+- `JAMBONES_DISABLE_AZURE_TTS_STREAMING` - Azure-specific streaming disable
+- `JAMBONES_TTS_CACHE_DURATION_MINS` - Cache TTL in minutes (default: 240)
+- `JAMBONES_TTS_TRIM_SILENCE` - Trim trailing silence from audio
+- `JAMBONES_TMP_FOLDER` - Temp folder for audio files (default: /tmp)
+- `JAMBONES_HTTP_PROXY_IP`, `JAMBONES_HTTP_PROXY_PORT` - HTTP proxy for Azure
+- `JAMBONES_AZURE_ENABLE_SSML` - Force SSML wrapper for Azure plain text
+
+## Key Dependencies
+
+- `@jambonz/realtimedb-helpers` - Redis client and hash utilities
+- `@google-cloud/text-to-speech` - Google TTS
+- `@aws-sdk/client-polly` - AWS Polly
+- `microsoft-cognitiveservices-speech-sdk` - Azure TTS
+- `@grpc/grpc-js` - gRPC for Riva
+- `openai` - OpenAI Whisper TTS
+- `bent` - HTTP client for REST-based vendors

lib/synth-audio.js

@@ -80,8 +80,8 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
   logger = logger || noopLogger;
 
   assert.ok(['google', 'aws', 'polly', 'microsoft', 'wellsaid', 'nvidia', 'elevenlabs',
-    'whisper', 'deepgram', 'deepgramflux', 'rimelabs', 'cartesia', 'nineninesix', 'inworld', 'resemble',
-    'murf', 'xai']
+    'whisper', 'deepgram', 'deepgramflux', 'rimelabs', 'cartesia', 'gradium', 'nineninesix', 'inworld', 'resemble',
+    'murf', 'xai', 'fishaudio']
     .includes(vendor) ||
   vendor.startsWith('custom'),
   `synthAudio supported vendors are google, aws, microsoft, nvidia and wellsaid ..etc, not ${vendor}`);
@@ -136,6 +136,9 @@ 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 ('gradium' === vendor) {
+    assert.ok(voice, 'synthAudio requires voice when gradium is used');
+    assert.ok(credentials.api_key, 'synthAudio requires api_key when gradium is used');
   } else if ('nineninesix' === vendor) {
     assert.ok(voice, 'synthAudio requires voice when nineninesix is used');
     assert.ok(credentials.api_key, 'synthAudio requires api_key when nineninesix is used');
@@ -146,6 +149,10 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
   } 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');
+  } else if ('fishaudio' === vendor) {
+    /* no voice assert: fish synthesizes with its own default voice when
+       reference_id is omitted, which is what the 'default' selection means */
+    assert.ok(credentials.api_key, 'synthAudio requires api_key when fishaudio is used');
   }
 
   const key = makeSynthKey({
@@ -217,6 +224,16 @@ async function synthAudio(client, createHash, retrieveHash, logger, stats, { acc
           credentials, options, stats, language, voice, key, text, renderForCaching, disableTtsStreaming,
           disableTtsCache});
         break;
+      case 'fishaudio':
+        audioData = await synthFishaudio(logger, {
+          credentials, options, stats, voice, key, text, renderForCaching, disableTtsStreaming,
+          disableTtsCache});
+        break;
+      case 'gradium':
+        audioData = await synthGradium(logger, {
+          credentials, options, stats, voice, key, text, renderForCaching, disableTtsStreaming,
+          disableTtsCache});
+        break;
       case 'nineninesix':
         audioData = await synthNineninesix(logger, {
           credentials, stats, language, voice, key, text, renderForCaching, disableTtsStreaming,
@@ -933,8 +950,9 @@ 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 {
@@ -1433,8 +1451,144 @@ const synthCartesia = async(logger, {
 
 };
 
+/* gradium.ai — json websocket for streaming, and a POST endpoint for the cache
+   render. only_audio:true + pcm_8000 returns bare little-endian 16-bit samples,
+   which is exactly the r8 container, so we avoid gradium's streaming wav header
+   (it carries 0xffffffff as the RIFF size, since length is unknown up front).
+*/
+const synthGradium = async(logger, {
+  credentials, options, stats, voice, key, text, renderForCaching, disableTtsStreaming, disableTtsCache
+}) => {
+  const {api_key, model_id} = credentials;
+  const {json_config, pronunciation_id} = options || {};
+
+  /* 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) {
+    let params = '{';
+    params += `api_key=${api_key}`;
+    params += `,playback_id=${key}`;
+    params += ',vendor=gradium';
+    params += `,voice=${voice}`;
+    params += `,write_cache_file=${disableTtsCache ? 0 : 1}`;
+    if (model_id) params += `,model_id=${model_id}`;
+    if (pronunciation_id) params += `,pronunciation_id=${pronunciation_id}`;
+    /* the say: param parser is brace-aware, so a nested json object survives intact */
+    if (json_config) {
+      params += `,json_config=${typeof json_config === 'string' ? json_config : JSON.stringify(json_config)}`;
+    }
+    params += '}';
+
+    return {
+      filePath: `say:${params}${text.replace(/\n/g, ' ').replace(/\r/g, ' ')}`,
+      servedFromCache: false,
+      rtt: 0
+    };
+  }
+
+  try {
+    const sampleRate = 8000;
+    const post = bent('https://api.gradium.ai', 'POST', 'buffer', {
+      'x-api-key': api_key,
+      'Content-Type': 'application/json'
+    });
+    const audioContent = await post('/api/post/speech/tts', {
+      text,
+      voice_id: voice,
+      model_name: model_id || 'default',
+      output_format: `pcm_${sampleRate}`,
+      only_audio: true,
+      ...(json_config && {json_config}),
+      ...(pronunciation_id && {pronunciation_id})
+    });
+    return {
+      audioContent,
+      extension: 'r8',
+      sampleRate
+    };
+  } catch (err) {
+    logger.info({err}, 'synth gradium returned error');
+    stats.increment('tts.count', ['vendor:gradium', 'accepted:no']);
+    throw err;
+  }
+};
+
 /* nineninesix.ai — a Cartesia-compatible API, but only raw/wav come back
    (mp3 is rejected), so the cache render asks for wav rather than mp3. */
+/* fish.audio — msgpack websocket for streaming, and a POST endpoint for the cache
+   render. format:pcm + sample_rate:8000 returns bare little-endian 16-bit samples,
+   which is exactly the r8 container. we avoid fish's wav output because its RIFF
+   header carries a placeholder size (0xffffff24) — length is unknown up front, as
+   with gradium.
+
+   fish is a voice-cloning vendor: the "voice" is a reference_id returned by
+   POST /model, and omitting it entirely synthesizes with fish's default voice.
+   the sentinel value 'default' (the bundled fallback entry in the portal) means
+   exactly that — send no reference_id.
+*/
+const synthFishaudio = async(logger, {
+  credentials, options, stats, voice, key, text, renderForCaching, disableTtsStreaming, disableTtsCache
+}) => {
+  const {api_key, model_id, fishaudio_tts_uri} = credentials;
+  const {reference_id, latency, chunk_length, speed, volume} = options || {};
+
+  /* free-text reference_id in the vendor options wins over the voice selector */
+  const refId = reference_id || (voice && voice !== 'default' ? voice : null);
+
+  /* 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) {
+    let params = '{';
+    params += `api_key=${api_key}`;
+    params += `,playback_id=${key}`;
+    params += ',vendor=fishaudio';
+    params += `,voice=${refId || 'default'}`;
+    params += `,write_cache_file=${disableTtsCache ? 0 : 1}`;
+    if (model_id) params += `,model_id=${model_id}`;
+    if (latency) params += `,latency=${latency}`;
+    if (chunk_length) params += `,chunk_length=${chunk_length}`;
+    if (speed) params += `,speed=${speed}`;
+    if (volume) params += `,volume=${volume}`;
+    if (fishaudio_tts_uri) params += `,endpoint=${fishaudio_tts_uri}`;
+    params += '}';
+
+    return {
+      filePath: `say:${params}${text.replace(/\n/g, ' ').replace(/\r/g, ' ')}`,
+      servedFromCache: false,
+      rtt: 0
+    };
+  }
+
+  try {
+    const sampleRate = 8000;
+    const post = bent(fishaudio_tts_uri || 'https://api.fish.audio', 'POST', 'buffer', {
+      'Authorization': `Bearer ${api_key}`,
+      'Content-Type': 'application/json',
+      /* the model is selected by header, not in the body */
+      'model': model_id || 's2.1-pro'
+    });
+    const audioContent = await post('/v1/tts', {
+      text,
+      format: 'pcm',
+      sample_rate: sampleRate,
+      ...(refId && {reference_id: refId}),
+      ...(latency && {latency}),
+      ...(chunk_length && {chunk_length: parseInt(chunk_length, 10)}),
+      ...((speed || volume) && {prosody: {
+        ...(speed && {speed: parseFloat(speed)}),
+        ...(volume && {volume: parseFloat(volume)})
+      }})
+    });
+    return {
+      audioContent,
+      extension: 'r8',
+      sampleRate
+    };
+  } catch (err) {
+    logger.info({err}, 'synth fishaudio returned error');
+    stats.increment('tts.count', ['vendor:fishaudio', 'accepted:no']);
+    throw err;
+  }
+};
+
 const synthNineninesix = async(logger, {
   credentials, stats, voice, language, key, text, renderForCaching, disableTtsStreaming, disableTtsCache
 }) => {

package-lock.json

@@ -1,15 +1,14 @@
 {
   "name": "@jambonz/speech-utils",
-  "version": "1.0.11",
+  "version": "1.0.18",
   "lockfileVersion": 2,
   "requires": true,
   "packages": {
     "": {
       "name": "@jambonz/speech-utils",
-      "version": "1.0.11",
+      "version": "1.0.18",
       "license": "MIT",
       "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",
@@ -19,9 +18,8 @@
         "bent": "^7.3.12",
         "debug": "^4.3.4",
         "google-protobuf": "^3.21.2",
-        "microsoft-cognitiveservices-speech-sdk": "1.38.0",
-        "openai": "^4.98.0",
-        "undici": "^7.5.0"
+        "microsoft-cognitiveservices-speech-sdk": "^1.51.0",
+        "openai": "^4.98.0"
       },
       "devDependencies": {
         "config": "^4.2.0",
@@ -760,6 +758,46 @@
         "node": ">=18.0.0"
       }
     },
+    "node_modules/@azure/abort-controller": {
+      "version": "2.2.0",
+      "resolved": "https://registry.npmjs.org/@azure/abort-controller/-/abort-controller-2.2.0.tgz",
+      "integrity": "sha512-fNAjWnA/nZ2jz31kxR/AqRaUT8ewHBw/WuBIosK0moMy1C9e5ValbDfFdIxJzVOOYaYkV/b2F1S4H/aHiqfVQg==",
+      "license": "MIT",
+      "dependencies": {
+        "tslib": "^2.6.2"
+      },
+      "engines": {
+        "node": ">=22.0.0"
+      }
+    },
+    "node_modules/@azure/core-auth": {
+      "version": "1.11.0",
+      "resolved": "https://registry.npmjs.org/@azure/core-auth/-/core-auth-1.11.0.tgz",
+      "integrity": "sha512-IUZydyTUkDnYdstOW9pFOOUQlBjAepK5teihDE3x6yxsPJs/hsAaaYpeGxdxrgtOiJbBKSjKW7MDk7AEhb4LRg==",
+      "license": "MIT",
+      "dependencies": {
+        "@azure/abort-controller": "^2.1.2",
+        "@azure/core-util": "^1.13.0",
+        "tslib": "^2.6.2"
+      },
+      "engines": {
+        "node": ">=22.0.0"
+      }
+    },
+    "node_modules/@azure/core-util": {
+      "version": "1.14.0",
+      "resolved": "https://registry.npmjs.org/@azure/core-util/-/core-util-1.14.0.tgz",
+      "integrity": "sha512-9n2pWK61veAuN0V20t9lOuoV4CFMdyAZ1ygZzvBGk/pBBJRib/PjL9PLXa/aI2CcPpyHfqVsxxqLCYl6uZlfDw==",
+      "license": "MIT",
+      "dependencies": {
+        "@azure/abort-controller": "^2.1.2",
+        "@typespec/ts-http-runtime": "^0.3.0",
+        "tslib": "^2.6.2"
+      },
+      "engines": {
+        "node": ">=22.0.0"
+      }
+    },
     "node_modules/@babel/code-frame": {
       "version": "7.26.2",
       "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.26.2.tgz",
@@ -2391,11 +2429,19 @@
       "resolved": "https://registry.npmjs.org/@types/webrtc/-/webrtc-0.0.37.tgz",
       "integrity": "sha512-JGAJC/ZZDhcrrmepU4sPLQLIOIAgs5oIK+Ieq90K8fdaNMhfdfqmYatJdgif1NDQtvrSlTOGJDUYHIDunuufOg=="
     },
-    "node_modules/23": {
-      "version": "0.0.0",
-      "resolved": "https://registry.npmjs.org/23/-/23-0.0.0.tgz",
-      "integrity": "sha512-uAETf9Okr72trtp1pNXYKhFCTTI1EKGcYMA8gw3jLGhlbaDX+grrNToEWrpt8luxRAvrZWBTvyB5wk3PpNjGQQ==",
-      "license": "ISC"
+    "node_modules/@typespec/ts-http-runtime": {
+      "version": "0.3.8",
+      "resolved": "https://registry.npmjs.org/@typespec/ts-http-runtime/-/ts-http-runtime-0.3.8.tgz",
+      "integrity": "sha512-bLMpVcWZNzq6lYOybwFwOAR1IXKcHnhUNqYeHjl1bET/qE3jFPFH+p8Wrh3rU4xwdnifPxmKNESBYnvnmc75aA==",
+      "license": "MIT",
+      "dependencies": {
+        "http-proxy-agent": "^7.0.0",
+        "https-proxy-agent": "^7.0.0",
+        "tslib": "^2.6.2"
+      },
+      "engines": {
+        "node": ">=22.0.0"
+      }
     },
     "node_modules/abort-controller": {
       "version": "3.0.0",
@@ -5278,17 +5324,18 @@
       }
     },
     "node_modules/microsoft-cognitiveservices-speech-sdk": {
-      "version": "1.38.0",
-      "resolved": "https://registry.npmjs.org/microsoft-cognitiveservices-speech-sdk/-/microsoft-cognitiveservices-speech-sdk-1.38.0.tgz",
-      "integrity": "sha512-NA6J4eIDkeR9iN83rcn77Kn5AWQcizDEn1tLMjzRvSovUNB1FrZe0mWYO0fsGltUwMl3Ns5OZ3lGw42PU4fEYA==",
+      "version": "1.51.0",
+      "resolved": "https://registry.npmjs.org/microsoft-cognitiveservices-speech-sdk/-/microsoft-cognitiveservices-speech-sdk-1.51.0.tgz",
+      "integrity": "sha512-BLLovv5PegOr5Lp52h4CSgL2c/ViFAh9LoU49ILNPyb/Z0giGI7nPV3xNLcmTtHLT+kfYNRGUIA62vORLzP8TA==",
       "license": "MIT",
       "dependencies": {
+        "@azure/core-auth": "^1.9.0",
         "@types/webrtc": "^0.0.37",
         "agent-base": "^6.0.1",
         "bent": "^7.3.12",
         "https-proxy-agent": "^4.0.0",
-        "uuid": "^9.0.0",
-        "ws": "^7.5.6"
+        "uuid": "^11.1.1",
+        "ws": "^8.21.0"
       }
     },
     "node_modules/microsoft-cognitiveservices-speech-sdk/node_modules/https-proxy-agent": {
@@ -5312,36 +5359,16 @@
       }
     },
     "node_modules/microsoft-cognitiveservices-speech-sdk/node_modules/uuid": {
-      "version": "9.0.1",
-      "resolved": "https://registry.npmjs.org/uuid/-/uuid-9.0.1.tgz",
-      "integrity": "sha512-b+1eJOlsR9K8HJpow9Ok3fiWOWSIcIzXodvv0rQjVoOVNpWMpxf1wZNpt4y9h10odCNrqnYp1OBzRktckBe3sA==",
+      "version": "11.1.1",
+      "resolved": "https://registry.npmjs.org/uuid/-/uuid-11.1.1.tgz",
+      "integrity": "sha512-vIYxrBCC/N/K+Js3qSN88go7kIfNPssr/hHCesKCQNAjmgvYS2oqr69kIufEG+O4+PfezOH4EbIeHCfFov8ZgQ==",
       "funding": [
         "https://github.com/sponsors/broofa",
         "https://github.com/sponsors/ctavan"
       ],
-      "bin": {
-        "uuid": "dist/bin/uuid"
-      }
-    },
-    "node_modules/microsoft-cognitiveservices-speech-sdk/node_modules/ws": {
-      "version": "7.5.10",
-      "resolved": "https://registry.npmjs.org/ws/-/ws-7.5.10.tgz",
-      "integrity": "sha512-+dbF1tHwZpXcbOJdVOkzLDxZP1ailvSxM6ZweXTegylPny803bFhA+vqBYw4s31NSAk4S2Qz+AKXK9a4wkdjcQ==",
       "license": "MIT",
-      "engines": {
-        "node": ">=8.3.0"
-      },
-      "peerDependencies": {
-        "bufferutil": "^4.0.1",
-        "utf-8-validate": "^5.0.2"
-      },
-      "peerDependenciesMeta": {
-        "bufferutil": {
-          "optional": true
-        },
-        "utf-8-validate": {
-          "optional": true
-        }
+      "bin": {
+        "uuid": "dist/esm/bin/uuid"
       }
     },
     "node_modules/mime-db": {
@@ -7031,15 +7058,6 @@
         "url": "https://github.com/sponsors/ljharb"
       }
     },
-    "node_modules/undici": {
-      "version": "7.24.5",
-      "resolved": "https://registry.npmjs.org/undici/-/undici-7.24.5.tgz",
-      "integrity": "sha512-3IWdCpjgxp15CbJnsi/Y9TCDE7HWVN19j1hmzVhoAkY/+CJx449tVxT5wZc1Gwg8J+P0LWvzlBzxYRnHJ+1i7Q==",
-      "license": "MIT",
-      "engines": {
-        "node": ">=20.18.1"
-      }
-    },
     "node_modules/undici-types": {
       "version": "5.26.5",
       "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz",
@@ -7342,11 +7360,6 @@
     }
   },
   "dependencies": {
-    "23": {
-      "version": "0.0.0",
-      "resolved": "https://registry.npmjs.org/23/-/23-0.0.0.tgz",
-      "integrity": "sha512-uAETf9Okr72trtp1pNXYKhFCTTI1EKGcYMA8gw3jLGhlbaDX+grrNToEWrpt8luxRAvrZWBTvyB5wk3PpNjGQQ=="
-    },
     "@aashutoshrathi/word-wrap": {
       "version": "1.2.6",
       "resolved": "https://registry.npmjs.org/@aashutoshrathi/word-wrap/-/word-wrap-1.2.6.tgz",
@@ -7924,6 +7937,34 @@
       "resolved": "https://registry.npmjs.org/@aws/lambda-invoke-store/-/lambda-invoke-store-0.2.4.tgz",
       "integrity": "sha512-iY8yvjE0y651BixKNPgmv1WrQc+GZ142sb0z4gYnChDDY2YqI4P/jsSopBWrKfAt7LOJAkOXt7rC/hms+WclQQ=="
     },
+    "@azure/abort-controller": {
+      "version": "2.2.0",
+      "resolved": "https://registry.npmjs.org/@azure/abort-controller/-/abort-controller-2.2.0.tgz",
+      "integrity": "sha512-fNAjWnA/nZ2jz31kxR/AqRaUT8ewHBw/WuBIosK0moMy1C9e5ValbDfFdIxJzVOOYaYkV/b2F1S4H/aHiqfVQg==",
+      "requires": {
+        "tslib": "^2.6.2"
+      }
+    },
+    "@azure/core-auth": {
+      "version": "1.11.0",
+      "resolved": "https://registry.npmjs.org/@azure/core-auth/-/core-auth-1.11.0.tgz",
+      "integrity": "sha512-IUZydyTUkDnYdstOW9pFOOUQlBjAepK5teihDE3x6yxsPJs/hsAaaYpeGxdxrgtOiJbBKSjKW7MDk7AEhb4LRg==",
+      "requires": {
+        "@azure/abort-controller": "^2.1.2",
+        "@azure/core-util": "^1.13.0",
+        "tslib": "^2.6.2"
+      }
+    },
+    "@azure/core-util": {
+      "version": "1.14.0",
+      "resolved": "https://registry.npmjs.org/@azure/core-util/-/core-util-1.14.0.tgz",
+      "integrity": "sha512-9n2pWK61veAuN0V20t9lOuoV4CFMdyAZ1ygZzvBGk/pBBJRib/PjL9PLXa/aI2CcPpyHfqVsxxqLCYl6uZlfDw==",
+      "requires": {
+        "@azure/abort-controller": "^2.1.2",
+        "@typespec/ts-http-runtime": "^0.3.0",
+        "tslib": "^2.6.2"
+      }
+    },
     "@babel/code-frame": {
       "version": "7.26.2",
       "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.26.2.tgz",
@@ -9118,6 +9159,16 @@
       "resolved": "https://registry.npmjs.org/@types/webrtc/-/webrtc-0.0.37.tgz",
       "integrity": "sha512-JGAJC/ZZDhcrrmepU4sPLQLIOIAgs5oIK+Ieq90K8fdaNMhfdfqmYatJdgif1NDQtvrSlTOGJDUYHIDunuufOg=="
     },
+    "@typespec/ts-http-runtime": {
+      "version": "0.3.8",
+      "resolved": "https://registry.npmjs.org/@typespec/ts-http-runtime/-/ts-http-runtime-0.3.8.tgz",
+      "integrity": "sha512-bLMpVcWZNzq6lYOybwFwOAR1IXKcHnhUNqYeHjl1bET/qE3jFPFH+p8Wrh3rU4xwdnifPxmKNESBYnvnmc75aA==",
+      "requires": {
+        "http-proxy-agent": "^7.0.0",
+        "https-proxy-agent": "^7.0.0",
+        "tslib": "^2.6.2"
+      }
+    },
     "abort-controller": {
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/abort-controller/-/abort-controller-3.0.0.tgz",
@@ -11106,16 +11157,17 @@
       "integrity": "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g=="
     },
     "microsoft-cognitiveservices-speech-sdk": {
-      "version": "1.38.0",
-      "resolved": "https://registry.npmjs.org/microsoft-cognitiveservices-speech-sdk/-/microsoft-cognitiveservices-speech-sdk-1.38.0.tgz",
-      "integrity": "sha512-NA6J4eIDkeR9iN83rcn77Kn5AWQcizDEn1tLMjzRvSovUNB1FrZe0mWYO0fsGltUwMl3Ns5OZ3lGw42PU4fEYA==",
+      "version": "1.51.0",
+      "resolved": "https://registry.npmjs.org/microsoft-cognitiveservices-speech-sdk/-/microsoft-cognitiveservices-speech-sdk-1.51.0.tgz",
+      "integrity": "sha512-BLLovv5PegOr5Lp52h4CSgL2c/ViFAh9LoU49ILNPyb/Z0giGI7nPV3xNLcmTtHLT+kfYNRGUIA62vORLzP8TA==",
       "requires": {
+        "@azure/core-auth": "^1.9.0",
         "@types/webrtc": "^0.0.37",
         "agent-base": "^6.0.1",
         "bent": "^7.3.12",
         "https-proxy-agent": "^4.0.0",
-        "uuid": "^9.0.0",
-        "ws": "^7.5.6"
+        "uuid": "^11.1.1",
+        "ws": "^8.21.0"
       },
       "dependencies": {
         "https-proxy-agent": {
@@ -11135,15 +11187,9 @@
           }
         },
         "uuid": {
-          "version": "9.0.1",
-          "resolved": "https://registry.npmjs.org/uuid/-/uuid-9.0.1.tgz",
-          "integrity": "sha512-b+1eJOlsR9K8HJpow9Ok3fiWOWSIcIzXodvv0rQjVoOVNpWMpxf1wZNpt4y9h10odCNrqnYp1OBzRktckBe3sA=="
-        },
-        "ws": {
-          "version": "7.5.10",
-          "resolved": "https://registry.npmjs.org/ws/-/ws-7.5.10.tgz",
-          "integrity": "sha512-+dbF1tHwZpXcbOJdVOkzLDxZP1ailvSxM6ZweXTegylPny803bFhA+vqBYw4s31NSAk4S2Qz+AKXK9a4wkdjcQ==",
-          "requires": {}
+          "version": "11.1.1",
+          "resolved": "https://registry.npmjs.org/uuid/-/uuid-11.1.1.tgz",
+          "integrity": "sha512-vIYxrBCC/N/K+Js3qSN88go7kIfNPssr/hHCesKCQNAjmgvYS2oqr69kIufEG+O4+PfezOH4EbIeHCfFov8ZgQ=="
         }
       }
     },
@@ -12347,11 +12393,6 @@
         "which-boxed-primitive": "^1.0.2"
       }
     },
-    "undici": {
-      "version": "7.24.5",
-      "resolved": "https://registry.npmjs.org/undici/-/undici-7.24.5.tgz",
-      "integrity": "sha512-3IWdCpjgxp15CbJnsi/Y9TCDE7HWVN19j1hmzVhoAkY/+CJx449tVxT5wZc1Gwg8J+P0LWvzlBzxYRnHJ+1i7Q=="
-    },
     "undici-types": {
       "version": "5.26.5",
       "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jambonz/speech-utils",
-  "version": "1.0.11",
+  "version": "1.0.18",
   "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",
@@ -35,9 +34,8 @@
     "bent": "^7.3.12",
     "debug": "^4.3.4",
     "google-protobuf": "^3.21.2",
-    "microsoft-cognitiveservices-speech-sdk": "1.38.0",
-    "openai": "^4.98.0",
-    "undici": "^7.5.0"
+    "microsoft-cognitiveservices-speech-sdk": "^1.51.0",
+    "openai": "^4.98.0"
   },
   "devDependencies": {
     "config": "^4.2.0",

test/synth.js

@@ -1058,6 +1058,76 @@ test('Cartesia speech synth tests', async(t) => {
   client.quit();
 });
 
+test('gradium speech synth tests', async(t) => {
+  const fn = require('..');
+  const {synthAudio, client} = fn(opts, logger);
+
+  if (!process.env.GRADIUM_API_KEY) {
+    t.pass('skipping gradium speech synth tests since GRADIUM_API_KEY is not provided');
+    return t.end();
+  }
+  const text = 'Hi there and welcome to jambones! ' + Date.now();
+  try {
+    const opts = await synthAudio(stats, {
+      vendor: 'gradium',
+      credentials: {
+        api_key: process.env.GRADIUM_API_KEY,
+        model_id: 'default'
+      },
+      voice: 'YTpq7expH9539ERJ',
+      text,
+      renderForCaching: true
+    });
+    t.ok(!opts.servedFromCache, `successfully synthed gradium audio to ${opts.filePath}`);
+
+  } catch (err) {
+    console.error(JSON.stringify(err));
+    t.end(err);
+  }
+  client.quit();
+});
+
+test('fishaudio speech synth tests', async(t) => {
+  const fn = require('..');
+  const {synthAudio, client} = fn(opts, logger);
+
+  if (!process.env.FISHAUDIO_API_KEY) {
+    t.pass('skipping fishaudio speech synth tests since FISHAUDIO_API_KEY is not provided');
+    return t.end();
+  }
+  const text = 'Hi there and welcome to jambones! ' + Date.now();
+  try {
+    /* voice 'default' means "send no reference_id" — fish's own default voice */
+    const o = await synthAudio(stats, {
+      vendor: 'fishaudio',
+      credentials: {
+        api_key: process.env.FISHAUDIO_API_KEY,
+        model_id: 's2.1-pro'
+      },
+      voice: 'default',
+      text,
+      renderForCaching: true
+    });
+    t.ok(!o.servedFromCache, `successfully synthed fishaudio audio to ${o.filePath}`);
+
+    /* the cache render must be raw 8k pcm (r8): fish's wav header carries a
+       placeholder RIFF size, so we never ask for wav */
+    const o2 = await synthAudio(stats, {
+      vendor: 'fishaudio',
+      credentials: {api_key: process.env.FISHAUDIO_API_KEY},
+      voice: 'default',
+      text: text + ' two',
+      renderForCaching: true,
+      disableTtsCache: true
+    });
+    t.ok(!o2.servedFromCache, 'fishaudio synthed a second uncached render');
+  } catch (err) {
+    console.error(JSON.stringify(err));
+    t.end(err);
+  }
+  client.quit();
+});
+
 test('nineninesix speech synth tests', async(t) => {
   const fn = require('..');
   const {synthAudio, client} = fn(opts, logger);
@@ -1075,7 +1145,7 @@ test('nineninesix speech synth tests', async(t) => {
         model_id: 'gepard-1.0'
       },
       language: 'en',
-      voice: '3ad7a827-7fd1-4954-bf35-47d4cc33d9ed',
+      voice: '775e4dfd-819c-4325-92ec-250f487ef7e3',
       text,
       renderForCaching: true
     });
@@ -1118,6 +1188,69 @@ 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);