support add google voice cloning key (#358)

* support add google voice cloning key * update upgrade db script * wip
2025-12-19 05:47:46 +00:00 · 2024-11-04 19:10:42 +07:00
parent 5c7bac91a8
commit e908f5830c
6 changed files with 225 additions and 18 deletions
--- a/db/jambones-sql.sql
+++ b/db/jambones-sql.sql
@@ -351,6 +351,8 @@ speech_credential_sid CHAR(36) NOT NULL,
 model VARCHAR(512) NOT NULL,
 reported_usage ENUM('REPORTED_USAGE_UNSPECIFIED','REALTIME','OFFLINE') DEFAULT 'REALTIME',
 name VARCHAR(64) NOT NULL,
+voice_cloning_key MEDIUMTEXT,
+use_voice_cloning_key BOOLEAN DEFAULT false,
 PRIMARY KEY (google_custom_voice_sid)
 );

--- a/db/jambones.sqs
+++ b/db/jambones.sqs
@@ -2082,7 +2082,7 @@
        </location>
        <size>
            <width>521.00</width>
-            <height>120.00</height>
+            <height>160.00</height>
        </size>
        <zorder>37</zorder>
        <SQLField>
@@ -2131,6 +2131,19 @@
            <notNull><![CDATA[1]]></notNull>
            <uid><![CDATA[D22EED9A-3502-489E-BE0A-5609B76697A8]]></uid>
        </SQLField>
+        <SQLField>
+            <name><![CDATA[voice_cloning_key]]></name>
+            <type><![CDATA[MEDIUMTEXT]]></type>
+            <notNull><![CDATA[0]]></notNull>
+            <uid><![CDATA[8A59864C-AA4F-4D2C-A88C-CA600D2BE425]]></uid>
+        </SQLField>
+        <SQLField>
+            <name><![CDATA[use_voice_cloning_key]]></name>
+            <type><![CDATA[BOOLEAN]]></type>
+            <defaultValue><![CDATA[false]]></defaultValue>
+            <forcedUnique><![CDATA[0]]></forcedUnique>
+            <uid><![CDATA[880D737F-D28E-4EC5-9A1F-6535326C376D]]></uid>
+        </SQLField>
        <labelWindowIndex><![CDATA[1]]></labelWindowIndex>
        <ui.treeExpanded><![CDATA[1]]></ui.treeExpanded>
        <uid><![CDATA[B83321B9-0B89-4E5F-95D4-864ADE2EC405]]></uid>
@@ -3131,17 +3144,17 @@
        <overviewPanelHidden><![CDATA[0]]></overviewPanelHidden>
        <pageBoundariesVisible><![CDATA[0]]></pageBoundariesVisible>
        <PageGridVisible><![CDATA[0]]></PageGridVisible>
-        <RightSidebarWidth><![CDATA[1485.000000]]></RightSidebarWidth>
+        <RightSidebarWidth><![CDATA[1403.000000]]></RightSidebarWidth>
        <sidebarIndex><![CDATA[2]]></sidebarIndex>
        <snapToGrid><![CDATA[0]]></snapToGrid>
        <SourceSidebarWidth><![CDATA[312.000000]]></SourceSidebarWidth>
        <SQLEditorFileFormatVersion><![CDATA[4]]></SQLEditorFileFormatVersion>
        <uid><![CDATA[58C99A00-06C9-478C-A667-C63842E088F3]]></uid>
-        <windowHeight><![CDATA[1055.000000]]></windowHeight>
-        <windowLocationX><![CDATA[1728.000000]]></windowLocationX>
-        <windowLocationY><![CDATA[37.000000]]></windowLocationY>
-        <windowScrollOrigin><![CDATA[{499, 0}]]></windowScrollOrigin>
-        <windowWidth><![CDATA[1920.000000]]></windowWidth>
+        <windowHeight><![CDATA[1079.000000]]></windowHeight>
+        <windowLocationX><![CDATA[48.000000]]></windowLocationX>
+        <windowLocationY><![CDATA[0.000000]]></windowLocationY>
+        <windowScrollOrigin><![CDATA[{969, 523}]]></windowScrollOrigin>
+        <windowWidth><![CDATA[1680.000000]]></windowWidth>
    </SQLDocumentInfo>
    <AllowsIndexRenamingOnInsert><![CDATA[1]]></AllowsIndexRenamingOnInsert>
    <defaultLabelExpanded><![CDATA[1]]></defaultLabelExpanded>
--- a/db/upgrade-jambonz-db.js
+++ b/db/upgrade-jambonz-db.js
@@ -202,6 +202,8 @@ const sql = {
    'ALTER TABLE system_information ADD COLUMN private_network_cidr VARCHAR(8192)',
    'ALTER TABLE system_information ADD COLUMN log_level ENUM(\'info\', \'debug\') NOT NULL DEFAULT \'info\'',
    'ALTER TABLE accounts ADD COLUMN enable_debug_log BOOLEAN NOT NULL DEFAULT false',
+    'ALTER TABLE google_custom_voices ADD COLUMN use_voice_cloning_key BOOLEAN DEFAULT false',
+    'ALTER TABLE google_custom_voices ADD COLUMN voice_cloning_key MEDIUMTEXT',
  ]
 };

--- a/lib/routes/api/google-custom-voices.js
+++ b/lib/routes/api/google-custom-voices.js
@@ -4,6 +4,9 @@ const SpeechCredential = require('../../models/speech-credential');
 const decorate = require('./decorate');
 const {DbErrorBadRequest, DbErrorForbidden} = require('../../utils/errors');
 const sysError = require('../error');
+const multer = require('multer');
+const upload = multer({ dest: '/tmp/csv/' });
+const fs = require('fs');

 const validateCredentialPermission = async(req) => {
  const credential = await SpeechCredential.retrieve(req.body.speech_credential_sid);
@@ -41,6 +44,33 @@ const preconditions = {

 decorate(router, GoogleCustomVoice, ['add', 'retrieve', 'update', 'delete'], preconditions);

+const voiceCloningKeySubString = (voice_cloning_key) => {
+  return voice_cloning_key ? voice_cloning_key.substring(0, 100) + '...' : undefined;
+};
+
+router.get('/: sid', async(req, res) => {
+  const logger = req.app.locals.logger;
+  try {
+    const {sid} = req.params;
+    const account_sid = req.user.account_sid;
+    const service_provider_sid = req.user.service_provider_sid;
+
+    const google_voice = await GoogleCustomVoice.retrieve(sid);
+    google_voice.voice_cloning_key = voiceCloningKeySubString(google_voice.voice_cloning_key);
+    if (!google_voice) {
+      return res.sendStatus(404);
+    }
+    if (req.user.hasScope('service_provider') && google_voice.service_provider_sid !== service_provider_sid ||
+      req.user.hasScope('account') && google_voice.account_sid !== account_sid) {
+      throw new DbErrorForbidden('Insufficient privileges');
+    }
+
+    return res.status(200).json(google_voice);
+  } catch (err) {
+    sysError(logger, res, err);
+  }
+});
+
 router.get('/', async(req, res) => {
  const logger = req.app.locals.logger;
  const account_sid = req.user.account_sid || req.query.account_sid;
@@ -67,7 +97,37 @@ router.get('/', async(req, res) => {
      }
      results = await GoogleCustomVoice.retrieveAllByLabel(service_provider_sid, account_sid, label);
    }
-    res.status(200).json(results);
+    res.status(200).json(results.map((r) => {
+      r.voice_cloning_key = voiceCloningKeySubString(r.voice_cloning_key);
+      return r;
+    }));
+  } catch (err) {
+    sysError(logger, res, err);
+  }
+});
+
+router.post('/:sid/VoiceCloningKey', upload.single('file'), async(req, res) => {
+  const {logger} = req.app.locals;
+  const {sid} = req.params;
+  const account_sid = req.user.account_sid;
+  const service_provider_sid = req.user.service_provider_sid;
+  try {
+    const google_voice = await GoogleCustomVoice.retrieve(sid);
+    if (!google_voice) {
+      return res.sendStatus(404);
+    }
+    if (req.user.hasScope('service_provider') && google_voice.service_provider_sid !== service_provider_sid ||
+      req.user.hasScope('account') && google_voice.account_sid !== account_sid) {
+      throw new DbErrorForbidden('Insufficient privileges');
+    }
+
+    const voice_cloning_key = Buffer.from(fs.readFileSync(req.file.path)).toString();
+    await GoogleCustomVoice.update(sid, {
+      voice_cloning_key
+    });
+    fs.unlinkSync(req.file.path);
+    return res.sendStatus(204);
+
  } catch (err) {
    sysError(logger, res, err);
  }
--- a/package-lock.json
+++ b/package-lock.json
@@ -19,7 +19,7 @@
        "@jambonz/lamejs": "^1.2.2",
        "@jambonz/mw-registrar": "^0.2.7",
        "@jambonz/realtimedb-helpers": "^0.8.10",
-        "@jambonz/speech-utils": "^0.1.20",
+        "@jambonz/speech-utils": "^0.1.21",
        "@jambonz/time-series": "^0.2.8",
        "@jambonz/verb-specifications": "^0.0.72",
        "@soniox/soniox-node": "^1.2.2",
@@ -36,6 +36,7 @@
        "jsonwebtoken": "^9.0.2",
        "mailgun.js": "^10.2.1",
        "microsoft-cognitiveservices-speech-sdk": "1.36.0",
+        "multer": "^1.4.5-lts.1",
        "mysql2": "^3.11.0",
        "nocache": "4.0.0",
        "passport": "^0.7.0",
@@ -1984,9 +1985,10 @@
      }
    },
    "node_modules/@google-cloud/text-to-speech": {
-      "version": "5.2.0",
-      "resolved": "https://registry.npmjs.org/@google-cloud/text-to-speech/-/text-to-speech-5.2.0.tgz",
-      "integrity": "sha512-N05ecDkKOgiBcSZmJlWpqR6nb8HOPGjOlTp+sdY1tNlZYV8UwsseRcuEM32ReU8n95+cCp+q8D4YCucFJ/DSsA==",
+      "version": "5.5.0",
+      "resolved": "https://registry.npmjs.org/@google-cloud/text-to-speech/-/text-to-speech-5.5.0.tgz",
+      "integrity": "sha512-Cw/UK2Y3l31Vsuozu8cxsmVS/09fShimes0tRLgDbOY2ZMG1Dckb6Zf/Q3Nxg4X0feFep44pvwNmyHKrOnl9SQ==",
+      "license": "Apache-2.0",
      "dependencies": {
        "google-gax": "^4.0.3"
      },
@@ -2224,13 +2226,14 @@
      }
    },
    "node_modules/@jambonz/speech-utils": {
-      "version": "0.1.20",
-      "resolved": "https://registry.npmjs.org/@jambonz/speech-utils/-/speech-utils-0.1.20.tgz",
-      "integrity": "sha512-3Ff9zLcFoVZhrI4jBKyjgWpv/fEMx1BpJP85daRwZNC2S0BFshULJ54fQxc8S63IsdgFf6g1cLD5VxqPaqCfbQ==",
+      "version": "0.1.21",
+      "resolved": "https://registry.npmjs.org/@jambonz/speech-utils/-/speech-utils-0.1.21.tgz",
+      "integrity": "sha512-o3qXMA0c4X5/THlNA4pwl72srdrNL+XlES5FxuMa+DM2k9VRxzrJqk0uRU2zCCVPfy9t53W+4h02DDKVqu/KSg==",
+      "license": "MIT",
      "dependencies": {
        "@aws-sdk/client-polly": "^3.496.0",
        "@aws-sdk/client-sts": "^3.496.0",
-        "@google-cloud/text-to-speech": "^5.0.2",
+        "@google-cloud/text-to-speech": "^5.5.0",
        "@grpc/grpc-js": "^1.9.14",
        "@jambonz/realtimedb-helpers": "^0.8.7",
        "bent": "^7.3.12",
@@ -3742,6 +3745,12 @@
      "resolved": "https://registry.npmjs.org/any-base/-/any-base-1.1.0.tgz",
      "integrity": "sha512-uMgjozySS8adZZYePpaWs8cxB9/kdzmpX6SgJZ+wbz1K5eYk5QMYDVJaZKhxyIHUdnnJkfR7SVgStgH7LkGUyg=="
    },
+    "node_modules/append-field": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/append-field/-/append-field-1.0.0.tgz",
+      "integrity": "sha512-klpgFSWLW1ZEs8svjfb7g4qWY0YS5imI82dTg+QahUvJ8YqAY0P10Uk8tTyh9ZGuYEZEMaeJYCF5BFuX552hsw==",
+      "license": "MIT"
+    },
    "node_modules/append-transform": {
      "version": "2.0.0",
      "resolved": "https://registry.npmjs.org/append-transform/-/append-transform-2.0.0.tgz",
@@ -4166,6 +4175,17 @@
        "node": ">=6.14.2"
      }
    },
+    "node_modules/busboy": {
+      "version": "1.6.0",
+      "resolved": "https://registry.npmjs.org/busboy/-/busboy-1.6.0.tgz",
+      "integrity": "sha512-8SFQbg/0hQ9xy3UNTB0YEnsNBbWfhf7RtnzpL7TkBiTBRfrQ9Fxcnz7VJsleJpyp6rVLvXiuORqjlHi5q+PYuA==",
+      "dependencies": {
+        "streamsearch": "^1.1.0"
+      },
+      "engines": {
+        "node": ">=10.16.0"
+      }
+    },
    "node_modules/bytes": {
      "version": "3.1.2",
      "resolved": "https://registry.npmjs.org/bytes/-/bytes-3.1.2.tgz",
@@ -4359,6 +4379,57 @@
      "resolved": "https://registry.npmjs.org/concat-map/-/concat-map-0.0.1.tgz",
      "integrity": "sha512-/Srv4dswyQNBfohGpz9o6Yb3Gz3SrUDqBH5rTuhGR7ahtlbYKnVxw2bCFMRljaA7EXHaXZ8wsHdodFvbkhKmqg=="
    },
+    "node_modules/concat-stream": {
+      "version": "1.6.2",
+      "resolved": "https://registry.npmjs.org/concat-stream/-/concat-stream-1.6.2.tgz",
+      "integrity": "sha512-27HBghJxjiZtIk3Ycvn/4kbJk/1uZuJFfuPEns6LaEvpvG1f0hTea8lilrouyo9mVc2GWdcEZ8OLoGmSADlrCw==",
+      "engines": [
+        "node >= 0.8"
+      ],
+      "license": "MIT",
+      "dependencies": {
+        "buffer-from": "^1.0.0",
+        "inherits": "^2.0.3",
+        "readable-stream": "^2.2.2",
+        "typedarray": "^0.0.6"
+      }
+    },
+    "node_modules/concat-stream/node_modules/isarray": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/isarray/-/isarray-1.0.0.tgz",
+      "integrity": "sha512-VLghIWNM6ELQzo7zwmcg0NmTVyWKYjvIeM83yjp0wRDTmUnrM678fQbcKBo6n2CJEF0szoG//ytg+TKla89ALQ==",
+      "license": "MIT"
+    },
+    "node_modules/concat-stream/node_modules/readable-stream": {
+      "version": "2.3.8",
+      "resolved": "https://registry.npmjs.org/readable-stream/-/readable-stream-2.3.8.tgz",
+      "integrity": "sha512-8p0AUk4XODgIewSi0l8Epjs+EVnWiK7NoDIEGU0HhE7+ZyY8D1IMY7odu5lRrFXGg71L15KG8QrPmum45RTtdA==",
+      "license": "MIT",
+      "dependencies": {
+        "core-util-is": "~1.0.0",
+        "inherits": "~2.0.3",
+        "isarray": "~1.0.0",
+        "process-nextick-args": "~2.0.0",
+        "safe-buffer": "~5.1.1",
+        "string_decoder": "~1.1.1",
+        "util-deprecate": "~1.0.1"
+      }
+    },
+    "node_modules/concat-stream/node_modules/safe-buffer": {
+      "version": "5.1.2",
+      "resolved": "https://registry.npmjs.org/safe-buffer/-/safe-buffer-5.1.2.tgz",
+      "integrity": "sha512-Gd2UZBJDkXlY7GbJxfsE8/nvKkUEU1G38c1siN6QP6a9PT9MmHB8GnpscSmMJSoF8LOIrt8ud/wPtojys4G6+g==",
+      "license": "MIT"
+    },
+    "node_modules/concat-stream/node_modules/string_decoder": {
+      "version": "1.1.1",
+      "resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-1.1.1.tgz",
+      "integrity": "sha512-n/ShnvDi6FHbbVfviro+WojiFzv+s8MPMHBczVePfUpDJLwoLT0ht1l4YwBCbi8pJAveEEdnkHyPyTP/mzRfwg==",
+      "license": "MIT",
+      "dependencies": {
+        "safe-buffer": "~5.1.0"
+      }
+    },
    "node_modules/content-disposition": {
      "version": "0.5.4",
      "resolved": "https://registry.npmjs.org/content-disposition/-/content-disposition-0.5.4.tgz",
@@ -7348,11 +7419,22 @@
      "version": "1.2.8",
      "resolved": "https://registry.npmjs.org/minimist/-/minimist-1.2.8.tgz",
      "integrity": "sha512-2yyAR8qBkN3YuheJanUpWC5U3bb5osDywNB8RzDVlDwDHbocAJveqqj1u8+SVD7jkWT4yvsHCpWqqWqAxb0zCA==",
-      "dev": true,
      "funding": {
        "url": "https://github.com/sponsors/ljharb"
      }
    },
+    "node_modules/mkdirp": {
+      "version": "0.5.6",
+      "resolved": "https://registry.npmjs.org/mkdirp/-/mkdirp-0.5.6.tgz",
+      "integrity": "sha512-FP+p8RB8OWpF3YZBCrP5gtADmtXApB5AMLn+vdyA+PyxCjrCs00mjyUozssO33cwDeT3wNGdLxJ5M//YqtHAJw==",
+      "license": "MIT",
+      "dependencies": {
+        "minimist": "^1.2.6"
+      },
+      "bin": {
+        "mkdirp": "bin/cmd.js"
+      }
+    },
    "node_modules/mock-property": {
      "version": "1.0.3",
      "resolved": "https://registry.npmjs.org/mock-property/-/mock-property-1.0.3.tgz",
@@ -7378,6 +7460,24 @@
      "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.2.tgz",
      "integrity": "sha512-sGkPx+VjMtmA6MX27oA4FBFELFCZZ4S4XqeGOXCv68tT+jb3vk/RyaKWP0PTKyWtmLSM0b+adUTEvbs1PEaH2w=="
    },
+    "node_modules/multer": {
+      "version": "1.4.5-lts.1",
+      "resolved": "https://registry.npmjs.org/multer/-/multer-1.4.5-lts.1.tgz",
+      "integrity": "sha512-ywPWvcDMeH+z9gQq5qYHCCy+ethsk4goepZ45GLD63fOu0YcNecQxi64nDs3qluZB+murG3/D4dJ7+dGctcCQQ==",
+      "license": "MIT",
+      "dependencies": {
+        "append-field": "^1.0.0",
+        "busboy": "^1.0.0",
+        "concat-stream": "^1.5.2",
+        "mkdirp": "^0.5.4",
+        "object-assign": "^4.1.1",
+        "type-is": "^1.6.4",
+        "xtend": "^4.0.0"
+      },
+      "engines": {
+        "node": ">= 6.0.0"
+      }
+    },
    "node_modules/mysql2": {
      "version": "3.11.0",
      "resolved": "https://registry.npmjs.org/mysql2/-/mysql2-3.11.0.tgz",
@@ -8228,6 +8328,12 @@
        "node": ">= 0.6.0"
      }
    },
+    "node_modules/process-nextick-args": {
+      "version": "2.0.1",
+      "resolved": "https://registry.npmjs.org/process-nextick-args/-/process-nextick-args-2.0.1.tgz",
+      "integrity": "sha512-3ouUOpQhtgrbOa17J7+uxOTpITYWaGP7/AhoR3+A+/1e9skrzelGi/dXzEYyvbxubEF6Wn2ypscTKiKJFFn1ag==",
+      "license": "MIT"
+    },
    "node_modules/process-on-spawn": {
      "version": "1.0.0",
      "resolved": "https://registry.npmjs.org/process-on-spawn/-/process-on-spawn-1.0.0.tgz",
@@ -9216,6 +9322,14 @@
      "resolved": "https://registry.npmjs.org/stream-shift/-/stream-shift-1.0.3.tgz",
      "integrity": "sha512-76ORR0DO1o1hlKwTbi/DM3EXWGf3ZJYO8cXX5RJwnul2DEg2oyoZyjLNoQM8WsvZiFKCRfC1O0J7iCvie3RZmQ=="
    },
+    "node_modules/streamsearch": {
+      "version": "1.1.0",
+      "resolved": "https://registry.npmjs.org/streamsearch/-/streamsearch-1.1.0.tgz",
+      "integrity": "sha512-Mcc5wHehp9aXz1ax6bZUyY5afg9u2rv5cqQI3mRrYkGC8rW2hM02jWuwjtL++LS5qinSyhj2QfLyNsuc+VsExg==",
+      "engines": {
+        "node": ">=10.0.0"
+      }
+    },
    "node_modules/string_decoder": {
      "version": "1.3.0",
      "resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-1.3.0.tgz",
@@ -9697,6 +9811,12 @@
        "url": "https://github.com/sponsors/ljharb"
      }
    },
+    "node_modules/typedarray": {
+      "version": "0.0.6",
+      "resolved": "https://registry.npmjs.org/typedarray/-/typedarray-0.0.6.tgz",
+      "integrity": "sha512-/aCDEGatGvZ2BIk+HmLf4ifCJFwvKFNb9/JeZPMulfgFracn9QFcAf5GO8B/mweUjSoblS5In0cWhqpfs/5PQA==",
+      "license": "MIT"
+    },
    "node_modules/typedarray-to-buffer": {
      "version": "3.1.5",
      "resolved": "https://registry.npmjs.org/typedarray-to-buffer/-/typedarray-to-buffer-3.1.5.tgz",
@@ -10109,6 +10229,15 @@
        "node": ">=4.0"
      }
    },
+    "node_modules/xtend": {
+      "version": "4.0.2",
+      "resolved": "https://registry.npmjs.org/xtend/-/xtend-4.0.2.tgz",
+      "integrity": "sha512-LKYU1iAXJXUgAXn9URjiu+MWhyUXHsvfp7mcuYm9dSUKK0/CjtrUwFAxD82/mCWbtLsGjFIad0wIsod4zrTAEQ==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=0.4"
+      }
+    },
    "node_modules/y18n": {
      "version": "5.0.8",
      "resolved": "https://registry.npmjs.org/y18n/-/y18n-5.0.8.tgz",
--- a/package.json
+++ b/package.json
@@ -29,7 +29,7 @@
    "@jambonz/lamejs": "^1.2.2",
    "@jambonz/mw-registrar": "^0.2.7",
    "@jambonz/realtimedb-helpers": "^0.8.10",
-    "@jambonz/speech-utils": "^0.1.20",
+    "@jambonz/speech-utils": "^0.1.21",
    "@jambonz/time-series": "^0.2.8",
    "@jambonz/verb-specifications": "^0.0.72",
    "@soniox/soniox-node": "^1.2.2",
@@ -46,6 +46,7 @@
    "jsonwebtoken": "^9.0.2",
    "mailgun.js": "^10.2.1",
    "microsoft-cognitiveservices-speech-sdk": "1.36.0",
+    "multer": "^1.4.5-lts.1",
    "mysql2": "^3.11.0",
    "nocache": "4.0.0",
    "passport": "^0.7.0",