whispermix 1.0.0

package/.gitattributes

@@ -0,0 +1,2 @@
+# Auto detect text files and perform LF normalization
+* text=auto

package/README.md

@@ -0,0 +1,94 @@
+# 🎙️ WhisperMix
+
+WhisperMix is a flexible module that provides an interface for transcribing audio using OpenAI's Whisper model or Groq's Whisper Large v3 model.
+
+## 📦 Installation
+
+```bash
+npm install whispermix
+```
+
+## ⚙️ Configuration
+
+Before using WhisperMix, you need to set up your environment variables:
+
+- For OpenAI's Whisper: Set `OPENAI_API_KEY` in your environment or `.env` file.
+- For Groq's Whisper Large v3: Set `GROQ_API_KEY` in your environment or `.env` file.
+
+## 🚀 Usage
+
+First, import the WhisperMix class:
+
+```javascript
+const WhisperMix = require('whispermix');
+```
+
+### 🔧 Initializing WhisperMix
+
+You can initialize WhisperMix with a specific model:
+
+```javascript
+const whisper = new WhisperMix({ model: 'whisper-1' }); // For OpenAI's Whisper
+// or
+const whisper = new WhisperMix({ model: 'whisper-large-v3' }); // For Groq's Whisper Large v3
+```
+
+### 📄 Transcribing from a File
+
+```javascript
+const filePath = 'path/to/your/audio/file.mp3';
+whisper.fromVoiceFile(filePath)
+  .then(transcription => console.log(transcription))
+  .catch(error => console.error(error));
+```
+
+### 🌊 Transcribing from a Stream
+
+```javascript
+const fs = require('fs');
+const audioStream = fs.createReadStream('path/to/your/audio/file.mp3');
+
+whisper.fromVoiceStream(audioStream)
+  .then(transcription => console.log(transcription))
+  .catch(error => console.error(error));
+```
+
+## 📚 API
+
+### `new WhisperMix(options)`
+
+Creates a new WhisperMix instance.
+
+- `options.model`: The model to use for transcription. Can be 'whisper-1' (OpenAI) or 'whisper-large-v3' (Groq).
+
+### `whisper.fromVoiceFile(filePath)`
+
+Transcribes audio from a file.
+
+- `filePath`: Path to the audio file.
+
+Returns a Promise that resolves with the transcription text.
+
+### `whisper.fromVoiceStream(audioStream)`
+
+Transcribes audio from a stream.
+
+- `audioStream`: A readable stream of the audio data.
+
+Returns a Promise that resolves with the transcription text.
+
+## ⚠️ Error Handling
+
+WhisperMix throws errors for API request failures. Always wrap your calls in try-catch blocks or use `.catch()` with promises to handle potential errors.
+
+## 📄 License
+
+The MIT License (MIT)
+
+Copyright (c) Martin Clasen
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

package/demo/default.env

@@ -0,0 +1,4 @@
+ANTHROPIC_API_KEY=""
+OPENAI_API_KEY=""
+PPLX_API_KEY=""
+GROQ_API_KEY=""

package/demo/groq.js

@@ -0,0 +1,11 @@
+const WhisperMix = require('../index.js')
+
+const transcribe = new WhisperMix({ model: 'whisper-1' });
+
+
+main(); async function main() {
+    const r = [];
+    r.push(transcribe.fromVoiceFile('./example.mp3'));
+    const x = await Promise.all(r).catch(console.log);
+    console.log(x)
+}

package/index.js

@@ -0,0 +1,62 @@
+const axios = require('axios');
+const FormData = require('form-data');
+const fs = require('fs');
+require('dotenv').config();
+
+class WhisperMix {
+    constructor(setup = { model: 'whisper-1' }) {
+        const config = {
+            'whisper-1': {
+                url: 'https://api.openai.com/v1/audio/transcriptions',
+                code: 'OPENAI',
+            },
+            'whisper-large-v3': {
+                url: 'https://api.groq.com/openai/v1/audio/transcriptions',
+                code: 'GROQ',
+            },
+        };
+
+        this.model = setup.model;
+        this.apiKey = process.env[config[this.model].code + '_API_KEY'];
+
+        Object.assign(this, setup)
+
+        this.apiUrl = config[this.model].url;
+
+    }
+
+    async fromVoiceFile(filePath) {
+        const formData = new FormData();
+        formData.append('file', fs.createReadStream(filePath));
+        formData.append('model', this.model);
+
+        return this._makeRequest(formData);
+    }
+
+    async fromVoiceStream(audioStream) {
+        return new Promise((resolve, reject) => {
+            const formData = new FormData();
+            formData.append('file', audioStream, { filename: 'audio.mp3' });
+            formData.append('model', this.model);
+
+            this._makeRequest(formData)
+                .then(resolve)
+                .catch(reject);
+        });
+    }
+
+    async _makeRequest(formData) {
+        try {
+            const response = await axios.post(this.apiUrl, formData, {
+                headers: {
+                    ...formData.getHeaders(),
+                    'Authorization': `Bearer ${this.apiKey}`,
+                },
+            });
+            return response.data.text.trim();
+        } catch (error) {
+            throw error.response ? error.response.data : error.message;
+        }
+    }
+}
+module.exports = WhisperMix

package/package.json

@@ -0,0 +1,45 @@
+{
+    "name": "whispermix",
+    "keywords": [
+        "whisper",
+        "openai",
+        "groq",
+        "transcription",
+        "speech-to-text",
+        "audio",
+        "voice",
+        "ai",
+        "machine-learning",
+        "nlp",
+        "natural-language-processing",
+        "audio-processing",
+        "voice-recognition",
+        "speech-recognition",
+        "api-wrapper",
+        "whisper-large-v3",
+        "whisper-1",
+        "streaming",
+        "file-processing",
+        "multilingual"
+    ],
+    "repository": {
+        "type": "git",
+        "url": "git+https://github.com/clasen/WhisperMix.git"
+    },
+    "version": "1.0.0",
+    "description": "",
+    "main": "index.js",
+    "scripts": {
+        "test": "echo \"Error: no test specified\" && exit 1"
+    },
+    "author": "Martin Clasen",
+    "license": "MIT",
+    "bugs": {
+        "url": "https://github.com/clasen/ModelMix/issues"
+    },
+    "dependencies": {
+        "axios": "^1.7.2",
+        "dotenv": "^16.4.5",
+        "form-data": "^4.0.0"
+    }
+}