multi-voice-sdk/package.json

A universal Text-to-Speech (TTS) and Speech-to-Text (STT) SDK supporting multiple providers (OpenAI, Google Gemini, Deepgram, Groq PlayAI, Cartesia, AssemblyAI) with audio merging capabilities

{
  "name": "multi-voice-sdk",
  "version": "1.1.0",
  "description": "A universal Text-to-Speech (TTS) and Speech-to-Text (STT) SDK supporting multiple providers (OpenAI, Google Gemini, Deepgram, Groq PlayAI, Cartesia, AssemblyAI) with audio merging capabilities",
  "main": "index.js",
  "type": "module",
  "exports": {
    ".": {
      "import": "./index.js",
      "types": "./index.d.ts"
    }
  },
  "files": [
    "index.js",
    "index.d.ts",
    "src/",
    "README.md",
    "LICENSE"
  ],
  "scripts": {
    "dev": "node example.js",
    "test": "echo \"Error: no test specified\" && exit 1"
  },
  "keywords": [
    "tts",
    "text-to-speech",
    "stt",
    "speech-to-text",
    "transcription",
    "audio",
    "openai",
    "gemini",
    "deepgram",
    "assemblyai",
    "groq",
    "playai",
    "cartesia",
    "voice",
    "speech-synthesis",
    "speech-recognition",
    "ai",
    "audio-processing"
  ],
  "author": "Akshay Kambli <https://github.com/ARK018>",
  "license": "ISC",
  "dependencies": {
    "@cartesia/cartesia-js": "^2.2.4",
    "@deepgram/sdk": "^4.2.0",
    "@google/genai": "^1.4.0",
    "assemblyai": "^4.13.3",
    "ffmpeg-static": "^5.2.0",
    "fluent-ffmpeg": "^2.1.3",
    "groq-sdk": "^0.25.0",
    "openai": "^5.1.1",
    "wav": "^1.0.2"
  },
  "devDependencies": {
    "dotenv": "^16.5.0"
  }
}