From 27addfa543263a3c7ced22e4bb1420a0bcb7db70 Mon Sep 17 00:00:00 2001 From: Hoan Luu Huu <110280845+xquanluu@users.noreply.github.com> Date: Thu, 22 Jan 2026 20:24:05 +0700 Subject: [PATCH] support google gemini tts (#534) * support google gemini tts * wip * wip * wip * wip * wip * support speech utils --- lib/routes/api/speech-credentials.js | 16 +- lib/utils/speech-utils.js | 8 +- package-lock.json | 595 ++++++++++++++++++++++++++- package.json | 2 +- test/speech-credentials.js | 109 +++++ 5 files changed, 706 insertions(+), 24 deletions(-) diff --git a/lib/routes/api/speech-credentials.js b/lib/routes/api/speech-credentials.js index f63118e..28eff1e 100644 --- a/lib/routes/api/speech-credentials.js +++ b/lib/routes/api/speech-credentials.js @@ -173,14 +173,23 @@ const encryptCredential = (obj) => { switch (vendor) { case 'google': assert(service_key, 'invalid json key: service_key is required'); + let modified_service_key = service_key; try { const o = JSON.parse(service_key); + // support google gemini tts + if (model_id) { + o.model_id = model_id; + } else { + delete o.model_id; + } + assert(o.client_email && o.private_key, 'invalid google service account key'); + modified_service_key = JSON.stringify(o); } catch (err) { assert(false, 'invalid google service account key - not JSON'); } - return encrypt(service_key); + return encrypt(modified_service_key); case 'aws': // AWS polly can work for 3 types of credentials: @@ -582,7 +591,7 @@ router.put('/:sid', async(req, res) => { custom_tts_url, custom_tts_streaming_url, cobalt_server_uri, - model_id, + model_id: model_id !== undefined ? model_id : o.model_id, stt_model_id, voice_engine, options, @@ -596,7 +605,8 @@ router.put('/:sid', async(req, res) => { resemble_tts_uri, resemble_tts_use_tls, api_uri, - houndify_server_uri + houndify_server_uri, + ...(vendor === 'google' && {service_key: JSON.stringify(o)}) }; logger.info({o, newCred}, 'updating speech credential with this new credential'); obj.credential = encryptCredential(newCred); diff --git a/lib/utils/speech-utils.js b/lib/utils/speech-utils.js index 40937b7..9867f9e 100644 --- a/lib/utils/speech-utils.js +++ b/lib/utils/speech-utils.js @@ -779,6 +779,7 @@ function decryptCredential(obj, credential, logger, isObscureKey = true) { o.private_key.slice(key_header.length, o.private_key.length)}` }; obj.service_key = JSON.stringify(obscured); + obj.model_id = o.model_id || null; } else if ('aws' === obj.vendor) { const o = JSON.parse(decrypt(credential)); @@ -1524,11 +1525,11 @@ function parseGooglelanguagesVoices(data) { return data.reduce((acc, voice) => { const languageCode = voice.languageCodes[0]; const existingLanguage = acc.find((lang) => lang.value === languageCode); - if (existingLanguage) { existingLanguage.voices.push({ value: voice.name, - name: `${voice.name.substring(languageCode.length + 1, voice.name.length)} (${voice.ssmlGender})` + name: `${voice.name.startsWith(languageCode) ? + voice.name.substring(languageCode.length + 1, voice.name.length) : voice.name} (${voice.ssmlGender})` }); } else { acc.push({ @@ -1536,7 +1537,8 @@ function parseGooglelanguagesVoices(data) { name: SttGoogleLanguagesVoices.find((lang) => lang.value === languageCode)?.name || languageCode, voices: [{ value: voice.name, - name: `${voice.name.substring(languageCode.length + 1, voice.name.length)} (${voice.ssmlGender})` + name: `${voice.name.startsWith(languageCode) ? + voice.name.substring(languageCode.length + 1, voice.name.length) : voice.name} (${voice.ssmlGender})` }] }); } diff --git a/package-lock.json b/package-lock.json index 4e008a3..bd7686f 100644 --- a/package-lock.json +++ b/package-lock.json @@ -21,7 +21,7 @@ "@jambonz/lamejs": "^1.2.2", "@jambonz/mw-registrar": "^0.2.7", "@jambonz/realtimedb-helpers": "^0.8.15", - "@jambonz/speech-utils": "^0.2.27", + "@jambonz/speech-utils": "^0.2.30", "@jambonz/time-series": "^0.2.8", "@jambonz/verb-specifications": "^0.0.122", "@soniox/soniox-node": "^1.2.2", @@ -3075,15 +3075,310 @@ } }, "node_modules/@google-cloud/text-to-speech": { - "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==", + "version": "6.4.0", + "resolved": "https://registry.npmjs.org/@google-cloud/text-to-speech/-/text-to-speech-6.4.0.tgz", + "integrity": "sha512-KUnK+mBYz9aegxHrBbwEignOkGRqXvqOXs/EGY7CAJhMFKuNSieW02/PV/ipVRsJM11MP69qgTgEetoyAN0HAg==", "license": "Apache-2.0", "dependencies": { - "google-gax": "^4.0.3" + "google-gax": "^5.0.0" }, "engines": { - "node": ">=14.0.0" + "node": ">=18" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/@grpc/grpc-js": { + "version": "1.14.3", + "resolved": "https://registry.npmjs.org/@grpc/grpc-js/-/grpc-js-1.14.3.tgz", + "integrity": "sha512-Iq8QQQ/7X3Sac15oB6p0FmUg/klxQvXLeileoqrTRGJYLV+/9tubbr9ipz0GKHjmXVsgFPo/+W+2cA8eNcR+XA==", + "license": "Apache-2.0", + "dependencies": { + "@grpc/proto-loader": "^0.8.0", + "@js-sdsl/ordered-map": "^4.4.2" + }, + "engines": { + "node": ">=12.10.0" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/@grpc/proto-loader": { + "version": "0.8.0", + "resolved": "https://registry.npmjs.org/@grpc/proto-loader/-/proto-loader-0.8.0.tgz", + "integrity": "sha512-rc1hOQtjIWGxcxpb9aHAfLpIctjEnsDehj0DAiVfBlmT84uvR0uUtN2hEi/ecvWVjXUGf5qPF4qEgiLOx1YIMQ==", + "license": "Apache-2.0", + "dependencies": { + "lodash.camelcase": "^4.3.0", + "long": "^5.0.0", + "protobufjs": "^7.5.3", + "yargs": "^17.7.2" + }, + "bin": { + "proto-loader-gen-types": "build/bin/proto-loader-gen-types.js" + }, + "engines": { + "node": ">=6" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/brace-expansion": { + "version": "2.0.2", + "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz", + "integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==", + "license": "MIT", + "dependencies": { + "balanced-match": "^1.0.0" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/foreground-child": { + "version": "3.3.1", + "resolved": "https://registry.npmjs.org/foreground-child/-/foreground-child-3.3.1.tgz", + "integrity": "sha512-gIXjKqtFuWEgzFRJA9WCQeSJLZDjgJUOMCMzxtvFq/37KojM1BFGufqsCy0r4qSQmYLsZYMeyRqzIWOMup03sw==", + "license": "ISC", + "dependencies": { + "cross-spawn": "^7.0.6", + "signal-exit": "^4.0.1" + }, + "engines": { + "node": ">=14" + }, + "funding": { + "url": "https://github.com/sponsors/isaacs" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/gaxios": { + "version": "7.1.3", + "resolved": "https://registry.npmjs.org/gaxios/-/gaxios-7.1.3.tgz", + "integrity": "sha512-YGGyuEdVIjqxkxVH1pUTMY/XtmmsApXrCVv5EU25iX6inEPbV+VakJfLealkBtJN69AQmh1eGOdCl9Sm1UP6XQ==", + "license": "Apache-2.0", + "dependencies": { + "extend": "^3.0.2", + "https-proxy-agent": "^7.0.1", + "node-fetch": "^3.3.2", + "rimraf": "^5.0.1" + }, + "engines": { + "node": ">=18" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/gcp-metadata": { + "version": "8.1.2", + "resolved": "https://registry.npmjs.org/gcp-metadata/-/gcp-metadata-8.1.2.tgz", + "integrity": "sha512-zV/5HKTfCeKWnxG0Dmrw51hEWFGfcF2xiXqcA3+J90WDuP0SvoiSO5ORvcBsifmx/FoIjgQN3oNOGaQ5PhLFkg==", + "license": "Apache-2.0", + "dependencies": { + "gaxios": "^7.0.0", + "google-logging-utils": "^1.0.0", + "json-bigint": "^1.0.0" + }, + "engines": { + "node": ">=18" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/glob": { + "version": "10.5.0", + "resolved": "https://registry.npmjs.org/glob/-/glob-10.5.0.tgz", + "integrity": "sha512-DfXN8DfhJ7NH3Oe7cFmu3NCu1wKbkReJ8TorzSAFbSKrlNaQSKfIzqYqVY8zlbs2NLBbWpRiU52GX2PbaBVNkg==", + "license": "ISC", + "dependencies": { + "foreground-child": "^3.1.0", + "jackspeak": "^3.1.2", + "minimatch": "^9.0.4", + "minipass": "^7.1.2", + "package-json-from-dist": "^1.0.0", + "path-scurry": "^1.11.1" + }, + "bin": { + "glob": "dist/esm/bin.mjs" + }, + "funding": { + "url": "https://github.com/sponsors/isaacs" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/google-auth-library": { + "version": "10.5.0", + "resolved": "https://registry.npmjs.org/google-auth-library/-/google-auth-library-10.5.0.tgz", + "integrity": "sha512-7ABviyMOlX5hIVD60YOfHw4/CxOfBhyduaYB+wbFWCWoni4N7SLcV46hrVRktuBbZjFC9ONyqamZITN7q3n32w==", + "license": "Apache-2.0", + "dependencies": { + "base64-js": "^1.3.0", + "ecdsa-sig-formatter": "^1.0.11", + "gaxios": "^7.0.0", + "gcp-metadata": "^8.0.0", + "google-logging-utils": "^1.0.0", + "gtoken": "^8.0.0", + "jws": "^4.0.0" + }, + "engines": { + "node": ">=18" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/google-gax": { + "version": "5.0.6", + "resolved": "https://registry.npmjs.org/google-gax/-/google-gax-5.0.6.tgz", + "integrity": "sha512-1kGbqVQBZPAAu4+/R1XxPQKP0ydbNYoLAr4l0ZO2bMV0kLyLW4I1gAk++qBLWt7DPORTzmWRMsCZe86gDjShJA==", + "license": "Apache-2.0", + "dependencies": { + "@grpc/grpc-js": "^1.12.6", + "@grpc/proto-loader": "^0.8.0", + "duplexify": "^4.1.3", + "google-auth-library": "^10.1.0", + "google-logging-utils": "^1.1.1", + "node-fetch": "^3.3.2", + "object-hash": "^3.0.0", + "proto3-json-serializer": "^3.0.0", + "protobufjs": "^7.5.3", + "retry-request": "^8.0.0", + "rimraf": "^5.0.1" + }, + "engines": { + "node": ">=18" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/gtoken": { + "version": "8.0.0", + "resolved": "https://registry.npmjs.org/gtoken/-/gtoken-8.0.0.tgz", + "integrity": "sha512-+CqsMbHPiSTdtSO14O51eMNlrp9N79gmeqmXeouJOhfucAedHw9noVe/n5uJk3tbKE6a+6ZCQg3RPhVhHByAIw==", + "license": "MIT", + "dependencies": { + "gaxios": "^7.0.0", + "jws": "^4.0.0" + }, + "engines": { + "node": ">=18" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/minimatch": { + "version": "9.0.5", + "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-9.0.5.tgz", + "integrity": "sha512-G6T0ZX48xgozx7587koeX9Ys2NYy6Gmv//P89sEte9V9whIapMNF4idKxnW2QtCcLiTWlb/wfCabAtAFWhhBow==", + "license": "ISC", + "dependencies": { + "brace-expansion": "^2.0.1" + }, + "engines": { + "node": ">=16 || 14 >=14.17" + }, + "funding": { + "url": "https://github.com/sponsors/isaacs" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/node-fetch": { + "version": "3.3.2", + "resolved": "https://registry.npmjs.org/node-fetch/-/node-fetch-3.3.2.tgz", + "integrity": "sha512-dRB78srN/l6gqWulah9SrxeYnxeddIG30+GOqK/9OlLVyLg3HPnr6SqOWTWOXKRwC2eGYCkZ59NNuSgvSrpgOA==", + "license": "MIT", + "dependencies": { + "data-uri-to-buffer": "^4.0.0", + "fetch-blob": "^3.1.4", + "formdata-polyfill": "^4.0.10" + }, + "engines": { + "node": "^12.20.0 || ^14.13.1 || >=16.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/node-fetch" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/proto3-json-serializer": { + "version": "3.0.4", + "resolved": "https://registry.npmjs.org/proto3-json-serializer/-/proto3-json-serializer-3.0.4.tgz", + "integrity": "sha512-E1sbAYg3aEbXrq0n1ojJkRHQJGE1kaE/O6GLA94y8rnJBfgvOPTOd1b9hOceQK1FFZI9qMh1vBERCyO2ifubcw==", + "license": "Apache-2.0", + "dependencies": { + "protobufjs": "^7.4.0" + }, + "engines": { + "node": ">=18" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/protobufjs": { + "version": "7.5.4", + "resolved": "https://registry.npmjs.org/protobufjs/-/protobufjs-7.5.4.tgz", + "integrity": "sha512-CvexbZtbov6jW2eXAvLukXjXUW1TzFaivC46BpWc/3BpcCysb5Vffu+B3XHMm8lVEuy2Mm4XGex8hBSg1yapPg==", + "hasInstallScript": true, + "license": "BSD-3-Clause", + "dependencies": { + "@protobufjs/aspromise": "^1.1.2", + "@protobufjs/base64": "^1.1.2", + "@protobufjs/codegen": "^2.0.4", + "@protobufjs/eventemitter": "^1.1.0", + "@protobufjs/fetch": "^1.1.0", + "@protobufjs/float": "^1.0.2", + "@protobufjs/inquire": "^1.1.0", + "@protobufjs/path": "^1.1.2", + "@protobufjs/pool": "^1.1.0", + "@protobufjs/utf8": "^1.1.0", + "@types/node": ">=13.7.0", + "long": "^5.0.0" + }, + "engines": { + "node": ">=12.0.0" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/retry-request": { + "version": "8.0.2", + "resolved": "https://registry.npmjs.org/retry-request/-/retry-request-8.0.2.tgz", + "integrity": "sha512-JzFPAfklk1kjR1w76f0QOIhoDkNkSqW8wYKT08n9yysTmZfB+RQ2QoXoTAeOi1HD9ZipTyTAZg3c4pM/jeqgSw==", + "license": "MIT", + "dependencies": { + "extend": "^3.0.2", + "teeny-request": "^10.0.0" + }, + "engines": { + "node": ">=18" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/rimraf": { + "version": "5.0.10", + "resolved": "https://registry.npmjs.org/rimraf/-/rimraf-5.0.10.tgz", + "integrity": "sha512-l0OE8wL34P4nJH/H2ffoaniAokM2qSmrtXHmlpvYr5AVVX8msAyW0l8NVJFDxlSK4u3Uh/f41cQheDVdnYijwQ==", + "license": "ISC", + "dependencies": { + "glob": "^10.3.7" + }, + "bin": { + "rimraf": "dist/esm/bin.mjs" + }, + "funding": { + "url": "https://github.com/sponsors/isaacs" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/signal-exit": { + "version": "4.1.0", + "resolved": "https://registry.npmjs.org/signal-exit/-/signal-exit-4.1.0.tgz", + "integrity": "sha512-bzyZ1e88w9O1iNJbKnOlvYTrWPDl46O1bG0D3XInv+9tkPrxrN8jUUTiFlDkkmKWgn1M6CfIA13SuGqOa9Korw==", + "license": "ISC", + "engines": { + "node": ">=14" + }, + "funding": { + "url": "https://github.com/sponsors/isaacs" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/teeny-request": { + "version": "10.1.0", + "resolved": "https://registry.npmjs.org/teeny-request/-/teeny-request-10.1.0.tgz", + "integrity": "sha512-3ZnLvgWF29jikg1sAQ1g0o+lr5JX6sVgYvfUJazn7ZjJroDBUTWp44/+cFVX0bULjv4vci+rBD+oGVAkWqhUbw==", + "license": "Apache-2.0", + "dependencies": { + "http-proxy-agent": "^5.0.0", + "https-proxy-agent": "^5.0.0", + "node-fetch": "^3.3.2", + "stream-events": "^1.0.5" + }, + "engines": { + "node": ">=18" + } + }, + "node_modules/@google-cloud/text-to-speech/node_modules/teeny-request/node_modules/https-proxy-agent": { + "version": "5.0.1", + "resolved": "https://registry.npmjs.org/https-proxy-agent/-/https-proxy-agent-5.0.1.tgz", + "integrity": "sha512-dFcAjpTQFgoLMzC2VwU+C/CbS7uRL0lWmxDITmqm7C+7F0Odmj6s9l6alZc6AELXhrnggM2CeWSXHGOdX2YtwA==", + "license": "MIT", + "dependencies": { + "agent-base": "6", + "debug": "4" + }, + "engines": { + "node": ">= 6" } }, "node_modules/@grpc/grpc-js": { @@ -3153,6 +3448,102 @@ "resolved": "https://registry.npmjs.org/@ioredis/commands/-/commands-1.2.0.tgz", "integrity": "sha512-Sx1pU8EM64o2BrqNpEO1CNLtKQwyhuXuqyfH7oGKCk+1a33d2r5saW8zNwm3j6BTExtjrv2BxTgzzkMwts6vGg==" }, + "node_modules/@isaacs/cliui": { + "version": "8.0.2", + "resolved": "https://registry.npmjs.org/@isaacs/cliui/-/cliui-8.0.2.tgz", + "integrity": "sha512-O8jcjabXaleOG9DQ0+ARXWZBTfnP4WNAqzuiJK7ll44AmxGKv/J2M4TPjxjY3znBCfvBXFzucm1twdyFybFqEA==", + "license": "ISC", + "dependencies": { + "string-width": "^5.1.2", + "string-width-cjs": "npm:string-width@^4.2.0", + "strip-ansi": "^7.0.1", + "strip-ansi-cjs": "npm:strip-ansi@^6.0.1", + "wrap-ansi": "^8.1.0", + "wrap-ansi-cjs": "npm:wrap-ansi@^7.0.0" + }, + "engines": { + "node": ">=12" + } + }, + "node_modules/@isaacs/cliui/node_modules/ansi-regex": { + "version": "6.2.2", + "resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-6.2.2.tgz", + "integrity": "sha512-Bq3SmSpyFHaWjPk8If9yc6svM8c56dB5BAtW4Qbw5jHTwwXXcTLoRMkpDJp6VL0XzlWaCHTXrkFURMYmD0sLqg==", + "license": "MIT", + "engines": { + "node": ">=12" + }, + "funding": { + "url": "https://github.com/chalk/ansi-regex?sponsor=1" + } + }, + "node_modules/@isaacs/cliui/node_modules/ansi-styles": { + "version": "6.2.3", + "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-6.2.3.tgz", + "integrity": "sha512-4Dj6M28JB+oAH8kFkTLUo+a2jwOFkuqb3yucU0CANcRRUbxS0cP0nZYCGjcc3BNXwRIsUVmDGgzawme7zvJHvg==", + "license": "MIT", + "engines": { + "node": ">=12" + }, + "funding": { + "url": "https://github.com/chalk/ansi-styles?sponsor=1" + } + }, + "node_modules/@isaacs/cliui/node_modules/emoji-regex": { + "version": "9.2.2", + "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-9.2.2.tgz", + "integrity": "sha512-L18DaJsXSUk2+42pv8mLs5jJT2hqFkFE4j21wOmgbUqsZ2hL72NsUU785g9RXgo3s0ZNgVl42TiHp3ZtOv/Vyg==", + "license": "MIT" + }, + "node_modules/@isaacs/cliui/node_modules/string-width": { + "version": "5.1.2", + "resolved": "https://registry.npmjs.org/string-width/-/string-width-5.1.2.tgz", + "integrity": "sha512-HnLOCR3vjcY8beoNLtcjZ5/nxn2afmME6lhrDrebokqMap+XbeW8n9TXpPDOqdGK5qcI3oT0GKTW6wC7EMiVqA==", + "license": "MIT", + "dependencies": { + "eastasianwidth": "^0.2.0", + "emoji-regex": "^9.2.2", + "strip-ansi": "^7.0.1" + }, + "engines": { + "node": ">=12" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/@isaacs/cliui/node_modules/strip-ansi": { + "version": "7.1.2", + "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-7.1.2.tgz", + "integrity": "sha512-gmBGslpoQJtgnMAvOVqGZpEz9dyoKTCzy2nfz/n8aIFhN/jCE/rCmcxabB6jOOHV+0WNnylOxaxBQPSvcWklhA==", + "license": "MIT", + "dependencies": { + "ansi-regex": "^6.0.1" + }, + "engines": { + "node": ">=12" + }, + "funding": { + "url": "https://github.com/chalk/strip-ansi?sponsor=1" + } + }, + "node_modules/@isaacs/cliui/node_modules/wrap-ansi": { + "version": "8.1.0", + "resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-8.1.0.tgz", + "integrity": "sha512-si7QWI6zUMq56bESFvagtmzMdGOtoxfR+Sez11Mobfc7tm+VkUckk9bW2UeffTGVUbOksxmSw0AA2gs8g71NCQ==", + "license": "MIT", + "dependencies": { + "ansi-styles": "^6.1.0", + "string-width": "^5.0.1", + "strip-ansi": "^7.0.1" + }, + "engines": { + "node": ">=12" + }, + "funding": { + "url": "https://github.com/chalk/wrap-ansi?sponsor=1" + } + }, "node_modules/@istanbuljs/load-nyc-config": { "version": "1.1.0", "resolved": "https://registry.npmjs.org/@istanbuljs/load-nyc-config/-/load-nyc-config-1.1.0.tgz", @@ -3317,16 +3708,16 @@ } }, "node_modules/@jambonz/speech-utils": { - "version": "0.2.27", - "resolved": "https://registry.npmjs.org/@jambonz/speech-utils/-/speech-utils-0.2.27.tgz", - "integrity": "sha512-wx0VKq2Gy8+pNx/RwMJjvaG7HT1/pezlgKkUfL0a4DoXxwIoglVyc/2SPUMf9yZ5xKSifYxcGoGSKfor9f9EbQ==", + "version": "0.2.30", + "resolved": "https://registry.npmjs.org/@jambonz/speech-utils/-/speech-utils-0.2.30.tgz", + "integrity": "sha512-FL0D5rx4KGgYbWRwjvxQDaI05AnKygYb0dL9O0MMfi8dOUBraGwp0X2Y6MfJaRKNM5mm77iwlsEd7nKP3J2h7Q==", "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", - "@google-cloud/text-to-speech": "^5.5.0", + "@google-cloud/text-to-speech": "^6.4.0", "@grpc/grpc-js": "^1.9.14", "@jambonz/realtimedb-helpers": "^0.8.7", "bent": "^7.3.12", @@ -3642,6 +4033,16 @@ "node": ">=10" } }, + "node_modules/@pkgjs/parseargs": { + "version": "0.11.0", + "resolved": "https://registry.npmjs.org/@pkgjs/parseargs/-/parseargs-0.11.0.tgz", + "integrity": "sha512-+1VkjdD0QBLPodGrJUeqarH8VAIvQODIbwh9XpP5Syisf7YoQgsJKPNFoqqLQlu+VQ/tVSshMR6loPMn8U+dPg==", + "license": "MIT", + "optional": true, + "engines": { + "node": ">=14" + } + }, "node_modules/@protobufjs/aspromise": { "version": "1.1.2", "resolved": "https://registry.npmjs.org/@protobufjs/aspromise/-/aspromise-1.1.2.tgz", @@ -5783,7 +6184,6 @@ "version": "7.0.6", "resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.6.tgz", "integrity": "sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA==", - "dev": true, "license": "MIT", "dependencies": { "path-key": "^3.1.0", @@ -5806,6 +6206,15 @@ "node": ">=0.12" } }, + "node_modules/data-uri-to-buffer": { + "version": "4.0.1", + "resolved": "https://registry.npmjs.org/data-uri-to-buffer/-/data-uri-to-buffer-4.0.1.tgz", + "integrity": "sha512-0R9ikRb668HB7QDxT1vkpuUBtqc53YyAwMwGeUFKRojY/NWKvdZ+9UYtRfGmhqNbRkTSVpMbmyhXipFFv2cb/A==", + "license": "MIT", + "engines": { + "node": ">= 12" + } + }, "node_modules/data-view-buffer": { "version": "1.0.1", "resolved": "https://registry.npmjs.org/data-view-buffer/-/data-view-buffer-1.0.1.tgz", @@ -6079,6 +6488,12 @@ "stream-shift": "^1.0.2" } }, + "node_modules/eastasianwidth": { + "version": "0.2.0", + "resolved": "https://registry.npmjs.org/eastasianwidth/-/eastasianwidth-0.2.0.tgz", + "integrity": "sha512-I88TYZWc9XiYHRQ4/3c5rjjfgkjhLyW2luGIheGERbNQ6OY7yTybanSpDXZa8y7VUP9YmDcYa+eyq4ca7iLqWA==", + "license": "MIT" + }, "node_modules/ecdsa-sig-formatter": { "version": "1.0.11", "resolved": "https://registry.npmjs.org/ecdsa-sig-formatter/-/ecdsa-sig-formatter-1.0.11.tgz", @@ -6820,6 +7235,38 @@ "reusify": "^1.0.4" } }, + "node_modules/fetch-blob": { + "version": "3.2.0", + "resolved": "https://registry.npmjs.org/fetch-blob/-/fetch-blob-3.2.0.tgz", + "integrity": "sha512-7yAQpD2UMJzLi1Dqv7qFYnPbaPx7ZfFK6PiIxQ4PfkGPyNyl2Ugx+a/umUonmKqjhM4DnfbMvdX6otXq83soQQ==", + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/jimmywarting" + }, + { + "type": "paypal", + "url": "https://paypal.me/jimmywarting" + } + ], + "license": "MIT", + "dependencies": { + "node-domexception": "^1.0.0", + "web-streams-polyfill": "^3.0.3" + }, + "engines": { + "node": "^12.20 || >= 14.13" + } + }, + "node_modules/fetch-blob/node_modules/web-streams-polyfill": { + "version": "3.3.3", + "resolved": "https://registry.npmjs.org/web-streams-polyfill/-/web-streams-polyfill-3.3.3.tgz", + "integrity": "sha512-d2JWLCivmZYTSIoge9MsgFCZrt571BikcWGYkjC1khllbTeDlGqZ2D8vD8E/lJa8WGWbb7Plm8/XJYV7IJHZZw==", + "license": "MIT", + "engines": { + "node": ">= 8" + } + }, "node_modules/file-entry-cache": { "version": "6.0.1", "resolved": "https://registry.npmjs.org/file-entry-cache/-/file-entry-cache-6.0.1.tgz", @@ -7026,6 +7473,18 @@ "node": ">= 12.20" } }, + "node_modules/formdata-polyfill": { + "version": "4.0.10", + "resolved": "https://registry.npmjs.org/formdata-polyfill/-/formdata-polyfill-4.0.10.tgz", + "integrity": "sha512-buewHzMvYL29jdeQTVILecSaZKnt/RJWjoZCF5OW60Z67/GmSLBkOFM7qh1PI3zFNtJbaZL5eQu1vLfazOwj4g==", + "license": "MIT", + "dependencies": { + "fetch-blob": "^3.1.2" + }, + "engines": { + "node": ">=12.20.0" + } + }, "node_modules/forwarded": { "version": "0.2.0", "resolved": "https://registry.npmjs.org/forwarded/-/forwarded-0.2.0.tgz", @@ -7316,6 +7775,15 @@ "node": ">=14" } }, + "node_modules/google-logging-utils": { + "version": "1.1.3", + "resolved": "https://registry.npmjs.org/google-logging-utils/-/google-logging-utils-1.1.3.tgz", + "integrity": "sha512-eAmLkjDjAFCVXg7A1unxHsLf961m6y17QFqXqAXGj/gVkKFrEICfStRfwUlGNfeCEjNRa32JEWOUTlYXPyyKvA==", + "license": "Apache-2.0", + "engines": { + "node": ">=14" + } + }, "node_modules/google-protobuf": { "version": "3.21.2", "resolved": "https://registry.npmjs.org/google-protobuf/-/google-protobuf-3.21.2.tgz", @@ -8295,8 +8763,7 @@ "node_modules/isexe": { "version": "2.0.0", "resolved": "https://registry.npmjs.org/isexe/-/isexe-2.0.0.tgz", - "integrity": "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw==", - "dev": true + "integrity": "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw==" }, "node_modules/isstream": { "version": "0.1.2", @@ -8430,6 +8897,21 @@ "node": ">=8" } }, + "node_modules/jackspeak": { + "version": "3.4.3", + "resolved": "https://registry.npmjs.org/jackspeak/-/jackspeak-3.4.3.tgz", + "integrity": "sha512-OGlZQpz2yfahA/Rd1Y8Cd9SIEsqvXkLVoSw/cgwhnhFMDbsQFeZYoJJ7bIZBS9BcamUW96asq/npPWugM+RQBw==", + "license": "BlueOak-1.0.0", + "dependencies": { + "@isaacs/cliui": "^8.0.2" + }, + "funding": { + "url": "https://github.com/sponsors/isaacs" + }, + "optionalDependencies": { + "@pkgjs/parseargs": "^0.11.0" + } + }, "node_modules/jest-diff": { "version": "27.5.1", "resolved": "https://registry.npmjs.org/jest-diff/-/jest-diff-27.5.1.tgz", @@ -8940,6 +9422,15 @@ "url": "https://github.com/sponsors/ljharb" } }, + "node_modules/minipass": { + "version": "7.1.2", + "resolved": "https://registry.npmjs.org/minipass/-/minipass-7.1.2.tgz", + "integrity": "sha512-qOOzS1cBTWYF4BH8fVePDBOO9iptMnGUEZwNc/cMWnTV2nVLZ7VoNWEPHkYczZA0pdoA7dl6e7FL659nX9S2aw==", + "license": "ISC", + "engines": { + "node": ">=16 || 14 >=14.17" + } + }, "node_modules/mkdirp": { "version": "0.5.6", "resolved": "https://registry.npmjs.org/mkdirp/-/mkdirp-0.5.6.tgz", @@ -9560,6 +10051,12 @@ "node": ">=8" } }, + "node_modules/package-json-from-dist": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/package-json-from-dist/-/package-json-from-dist-1.0.1.tgz", + "integrity": "sha512-UEZIS3/by4OC8vL3P2dTXRETpebLI2NiI5vIrjaD/5UtrkFX/tNbwjTSRAGC/+7CAo2pIcBaRgWmcBBHcsaCIw==", + "license": "BlueOak-1.0.0" + }, "node_modules/pako": { "version": "1.0.11", "resolved": "https://registry.npmjs.org/pako/-/pako-1.0.11.tgz", @@ -9643,7 +10140,6 @@ "version": "3.1.1", "resolved": "https://registry.npmjs.org/path-key/-/path-key-3.1.1.tgz", "integrity": "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q==", - "dev": true, "engines": { "node": ">=8" } @@ -9654,6 +10150,28 @@ "integrity": "sha512-LDJzPVEEEPR+y48z93A0Ed0yXb8pAByGWo/k5YYdYgpY2/2EsOsksJrq7lOHxryrVOn1ejG6oAp8ahvOIQD8sw==", "dev": true }, + "node_modules/path-scurry": { + "version": "1.11.1", + "resolved": "https://registry.npmjs.org/path-scurry/-/path-scurry-1.11.1.tgz", + "integrity": "sha512-Xa4Nw17FS9ApQFJ9umLiJS4orGjm7ZzwUrwamcGQuHSzDyth9boKDaycYdDcZDuqYATXw4HFXgaqWTctW/v1HA==", + "license": "BlueOak-1.0.0", + "dependencies": { + "lru-cache": "^10.2.0", + "minipass": "^5.0.0 || ^6.0.2 || ^7.0.0" + }, + "engines": { + "node": ">=16 || 14 >=14.18" + }, + "funding": { + "url": "https://github.com/sponsors/isaacs" + } + }, + "node_modules/path-scurry/node_modules/lru-cache": { + "version": "10.4.3", + "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-10.4.3.tgz", + "integrity": "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ==", + "license": "ISC" + }, "node_modules/path-to-regexp": { "version": "0.1.12", "resolved": "https://registry.npmjs.org/path-to-regexp/-/path-to-regexp-0.1.12.tgz", @@ -10518,7 +11036,6 @@ "version": "2.0.0", "resolved": "https://registry.npmjs.org/shebang-command/-/shebang-command-2.0.0.tgz", "integrity": "sha512-kHxr2zZpYtdmrN1qDjrrX/Z1rR1kG8Dx+gkpK1G4eXmvXswmcE1hTWBWYUzlraYw1/yZp6YuDY77YtvbN0dmDA==", - "dev": true, "dependencies": { "shebang-regex": "^3.0.0" }, @@ -10530,7 +11047,6 @@ "version": "3.0.0", "resolved": "https://registry.npmjs.org/shebang-regex/-/shebang-regex-3.0.0.tgz", "integrity": "sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A==", - "dev": true, "engines": { "node": ">=8" } @@ -10840,6 +11356,21 @@ "node": ">=8" } }, + "node_modules/string-width-cjs": { + "name": "string-width", + "version": "4.2.3", + "resolved": "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz", + "integrity": "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==", + "license": "MIT", + "dependencies": { + "emoji-regex": "^8.0.0", + "is-fullwidth-code-point": "^3.0.0", + "strip-ansi": "^6.0.1" + }, + "engines": { + "node": ">=8" + } + }, "node_modules/string.prototype.trim": { "version": "1.2.9", "resolved": "https://registry.npmjs.org/string.prototype.trim/-/string.prototype.trim-1.2.9.tgz", @@ -10900,6 +11431,19 @@ "node": ">=8" } }, + "node_modules/strip-ansi-cjs": { + "name": "strip-ansi", + "version": "6.0.1", + "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-6.0.1.tgz", + "integrity": "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A==", + "license": "MIT", + "dependencies": { + "ansi-regex": "^5.0.1" + }, + "engines": { + "node": ">=8" + } + }, "node_modules/strip-bom": { "version": "4.0.0", "resolved": "https://registry.npmjs.org/strip-bom/-/strip-bom-4.0.0.tgz", @@ -11564,7 +12108,6 @@ "version": "2.0.2", "resolved": "https://registry.npmjs.org/which/-/which-2.0.2.tgz", "integrity": "sha512-BLI3Tl1TW3Pvl70l3yq3Y64i+awpwXqsGBYWkkqMtnbXgrMD+yj7rhW0kuEDxzJaYXGjEW5ogapKNMEKNMjibA==", - "dev": true, "dependencies": { "isexe": "^2.0.0" }, @@ -11652,6 +12195,24 @@ "url": "https://github.com/chalk/wrap-ansi?sponsor=1" } }, + "node_modules/wrap-ansi-cjs": { + "name": "wrap-ansi", + "version": "7.0.0", + "resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-7.0.0.tgz", + "integrity": "sha512-YVGIj2kamLSTxw6NsZjoBxfSwsn0ycdesmc4p+Q21c5zPuZ1pl+NfxVdxPtdHvmNVOQ6XSYG4AUtyt/Fi7D16Q==", + "license": "MIT", + "dependencies": { + "ansi-styles": "^4.0.0", + "string-width": "^4.1.0", + "strip-ansi": "^6.0.0" + }, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/chalk/wrap-ansi?sponsor=1" + } + }, "node_modules/wrappy": { "version": "1.0.2", "resolved": "https://registry.npmjs.org/wrappy/-/wrappy-1.0.2.tgz", diff --git a/package.json b/package.json index 86f6335..c19e6a5 100644 --- a/package.json +++ b/package.json @@ -32,7 +32,7 @@ "@jambonz/lamejs": "^1.2.2", "@jambonz/mw-registrar": "^0.2.7", "@jambonz/realtimedb-helpers": "^0.8.15", - "@jambonz/speech-utils": "^0.2.27", + "@jambonz/speech-utils": "^0.2.30", "@jambonz/time-series": "^0.2.8", "@jambonz/verb-specifications": "^0.0.122", "@soniox/soniox-node": "^1.2.2", diff --git a/test/speech-credentials.js b/test/speech-credentials.js index d642dcb..7b80bb5 100644 --- a/test/speech-credentials.js +++ b/test/speech-credentials.js @@ -1136,6 +1136,115 @@ test('speech credentials tests', async(t) => { }); t.ok(result.body.stt.length !== 0, 'successfully get gladia supported languages and voices'); + /* add a credential for google with model_id */ + result = await request.post(`/Accounts/${account_sid}/SpeechCredentials`, { + resolveWithFullResponse: true, + auth: authUser, + json: true, + body: { + vendor: 'google', + label: 'google_gemini_tts', + service_key: jsonKey, + use_for_tts: true, + use_for_stt: true, + model_id: 'gemini-2.0-flash-exp' + } + }); + t.ok(result.statusCode === 201, 'successfully added speech credential for google with model_id'); + const google_gemini_sid = result.body.sid; + + /* query the credential and verify model_id are stored */ + result = await request.get(`/Accounts/${account_sid}/SpeechCredentials/${google_gemini_sid}`, { + resolveWithFullResponse: true, + auth: authAdmin, + json: true, + }); + t.ok(result.statusCode === 200, 'successfully retrieved google gemini speech credential'); + t.ok(result.body.vendor === 'google', 'vendor is google'); + t.ok(result.body.label === 'google_gemini_tts', 'label is correct'); + t.ok(result.body.model_id === 'gemini-2.0-flash-exp', 'model_id is correct'); + + /* update the credential to change model_id */ + result = await request.put(`/Accounts/${account_sid}/SpeechCredentials/${google_gemini_sid}`, { + resolveWithFullResponse: true, + auth: authUser, + json: true, + body: { + use_for_tts: true, + use_for_stt: true, + model_id: 'gemini-2.5-flash-preview-native-audio' + } + }); + t.ok(result.statusCode === 204, 'successfully updated google gemini speech credential'); + + /* verify the update */ + result = await request.get(`/Accounts/${account_sid}/SpeechCredentials/${google_gemini_sid}`, { + resolveWithFullResponse: true, + auth: authAdmin, + json: true, + }); + t.ok(result.statusCode === 200, 'successfully retrieved updated google gemini speech credential'); + t.ok(result.body.model_id === 'gemini-2.5-flash-preview-native-audio', 'model_id is updated correctly'); + + /* update the credential to disable gemini tts */ + result = await request.put(`/Accounts/${account_sid}/SpeechCredentials/${google_gemini_sid}`, { + resolveWithFullResponse: true, + auth: authUser, + json: true, + body: { + use_for_tts: true, + use_for_stt: true, + model_id: null + } + }); + t.ok(result.statusCode === 204, 'successfully updated google speech credential to disable gemini tts'); + + /* verify the update to disable gemini tts */ + result = await request.get(`/Accounts/${account_sid}/SpeechCredentials/${google_gemini_sid}`, { + resolveWithFullResponse: true, + auth: authAdmin, + json: true, + }); + t.ok(result.statusCode === 200, 'successfully retrieved google speech credential after disabling gemini'); + t.ok(!result.body.model_id, 'model_id is now null'); + + /* delete the google gemini credential */ + result = await request.delete(`/Accounts/${account_sid}/SpeechCredentials/${google_gemini_sid}`, { + auth: authUser, + resolveWithFullResponse: true, + }); + t.ok(result.statusCode === 204, 'successfully deleted google gemini speech credential'); + + /* add a credential for google at service provider level with gemini tts */ + result = await request.post(`/ServiceProviders/${service_provider_sid}/SpeechCredentials`, { + resolveWithFullResponse: true, + auth: authAdmin, + json: true, + body: { + vendor: 'google', + service_key: jsonKey, + use_for_tts: true, + use_for_stt: true, + model_id: 'gemini-2.0-flash-exp' + } + }); + t.ok(result.statusCode === 201, 'successfully added google gemini speech credential to service provider'); + const sp_google_gemini_sid = result.body.sid; + + /* query the service provider credential */ + result = await request.get(`/ServiceProviders/${service_provider_sid}/SpeechCredentials`, { + resolveWithFullResponse: true, + auth: authAdmin, + json: true, + }); + t.ok(result.statusCode === 200, 'successfully queried service provider speech credentials'); + const spCred = result.body.find(c => c.speech_credential_sid === sp_google_gemini_sid); + t.ok(spCred, 'found google gemini credential in service provider credentials'); + t.ok(spCred.model_id === 'gemini-2.0-flash-exp', 'model_id is correct for SP credential'); + + /* delete the service provider google gemini credential */ + await deleteObjectBySid(request, `/ServiceProviders/${service_provider_sid}/SpeechCredentials`, sp_google_gemini_sid); + await deleteObjectBySid(request, '/Accounts', account_sid); await deleteObjectBySid(request, '/ServiceProviders', service_provider_sid); t.end();