@charivo/stt-provider-openai 0.0.1

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Zeikar
+
+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/README.md

@@ -0,0 +1,297 @@
+# @charivo/stt-provider-openai
+
+OpenAI Whisper STT (Speech-to-Text) provider for Charivo framework (server-side).
+
+## ⚠️ Important Security Note
+
+This is a **server-side provider** that directly calls OpenAI Whisper API and should **ONLY** be used in Node.js/server environments. Using this in client-side code will expose your API key.
+
+For client-side usage, use [`@charivo/stt-transcriber-remote`](../stt-transcriber-remote) instead.
+
+## Architecture
+
+```
+Node.js Server → OpenAISTTProvider → OpenAI Whisper API
+```
+
+## Installation
+
+```bash
+pnpm add @charivo/stt-provider-openai @charivo/core openai
+```
+
+## Usage
+
+### Server-side Only
+
+```typescript
+import { createOpenAISTTProvider } from "@charivo/stt-provider-openai";
+
+const provider = createOpenAISTTProvider({
+  apiKey: process.env.OPENAI_API_KEY!, // Server environment variable
+  defaultModel: "whisper-1",
+  defaultLanguage: "en"
+});
+
+// Transcribe audio data
+const transcription = await provider.transcribe(audioBlob);
+
+// With custom options
+const transcription2 = await provider.transcribe(audioBlob, {
+  language: "es" // Spanish
+});
+```
+
+### API Endpoint Usage
+
+```typescript
+// Express.js example
+import express from 'express';
+import multer from 'multer';
+import { createOpenAISTTProvider } from "@charivo/stt-provider-openai";
+
+const app = express();
+const upload = multer({ storage: multer.memoryStorage() });
+const provider = createOpenAISTTProvider({
+  apiKey: process.env.OPENAI_API_KEY!
+});
+
+app.post('/api/stt', upload.single('audio'), async (req, res) => {
+  try {
+    if (!req.file) {
+      return res.status(400).json({ error: 'No audio file provided' });
+    }
+
+    const audioBlob = new Blob([req.file.buffer], { 
+      type: req.file.mimetype 
+    });
+    
+    const transcription = await provider.transcribe(audioBlob, {
+      language: req.body.language
+    });
+    
+    res.json({ transcription });
+  } catch (error) {
+    res.status(500).json({ error: 'Transcription failed' });
+  }
+});
+```
+
+### Next.js API Route Example
+
+```typescript
+// app/api/stt/route.ts
+import { NextRequest, NextResponse } from "next/server";
+import { createOpenAISTTProvider } from "@charivo/stt-provider-openai";
+
+const provider = createOpenAISTTProvider({
+  apiKey: process.env.OPENAI_API_KEY!
+});
+
+export async function POST(request: NextRequest) {
+  try {
+    const formData = await request.formData();
+    const audioFile = formData.get('audio') as File;
+    const language = formData.get('language') as string | undefined;
+
+    if (!audioFile) {
+      return NextResponse.json(
+        { error: "No audio file provided" },
+        { status: 400 }
+      );
+    }
+
+    // Convert File to Blob
+    const audioBlob = new Blob([await audioFile.arrayBuffer()], {
+      type: audioFile.type
+    });
+
+    const transcription = await provider.transcribe(audioBlob, {
+      language
+    });
+
+    return NextResponse.json({ transcription });
+  } catch (error) {
+    console.error("STT error:", error);
+    return NextResponse.json(
+      { error: "Failed to transcribe audio" },
+      { status: 500 }
+    );
+  }
+}
+```
+
+## API Reference
+
+### Configuration Options
+
+```typescript
+interface OpenAISTTConfig {
+  /** OpenAI API key (required) */
+  apiKey: string;
+  /** Default OpenAI Whisper model (default: "whisper-1") */
+  defaultModel?: "whisper-1";
+  /** Default language for transcription (e.g., "en", "es", "fr") */
+  defaultLanguage?: string;
+  /** Allow browser usage (dangerous - exposes API key) */
+  dangerouslyAllowBrowser?: boolean;
+}
+```
+
+### Available Models
+
+- `whisper-1` - OpenAI's Whisper model for speech recognition
+
+### Supported Languages
+
+Whisper supports 99+ languages including:
+- English (`en`)
+- Spanish (`es`)
+- French (`fr`)
+- German (`de`)
+- Chinese (`zh`)
+- Japanese (`ja`)
+- Korean (`ko`)
+- And many more...
+
+For best results, specify the language if known. If not specified, Whisper will auto-detect.
+
+### Methods
+
+#### `transcribe(audio, options?): Promise<string>`
+Transcribe audio data to text.
+
+```typescript
+// With Blob
+const transcription = await provider.transcribe(audioBlob);
+
+// With ArrayBuffer
+const transcription = await provider.transcribe(audioBuffer);
+
+// With language option
+const transcription = await provider.transcribe(audioBlob, {
+  language: "es"
+});
+```
+
+**Parameters:**
+- `audio: Blob | ArrayBuffer` - Audio data to transcribe
+- `options?: STTOptions` - Optional transcription options
+  - `language?: string` - Language code (e.g., "en", "es")
+
+**Returns:** `Promise<string>` - Transcribed text
+
+## Browser Usage (Not Recommended)
+
+⚠️ **Security Warning**: This provider should NOT be used in browser as it exposes your API key to users.
+
+**Better alternative**: Use [`@charivo/stt-transcriber-remote`](../stt-transcriber-remote) for client-side usage.
+
+## Environment Variables
+
+```bash
+OPENAI_API_KEY=your_openai_api_key_here
+```
+
+## Error Handling
+
+```typescript
+try {
+  const transcription = await provider.transcribe(audioBlob);
+} catch (error) {
+  console.error("Transcription failed:", error);
+  // Handle OpenAI API errors:
+  // - Invalid audio format
+  // - API key issues
+  // - Rate limiting
+  // - Network errors
+}
+```
+
+## Use Cases
+
+- **API Endpoints**: Provide STT service via your server
+- **Secure Transcription**: Keep API keys on server, expose via HTTP endpoint
+- **Language Support**: Leverage Whisper's multilingual capabilities
+- **Rate Limiting**: Control STT usage per user
+- **Cost Monitoring**: Track STT API usage and costs
+
+## Complete Example
+
+### Server (Next.js API Route)
+
+```typescript
+// app/api/stt/route.ts
+import { createOpenAISTTProvider } from "@charivo/stt-provider-openai";
+
+const provider = createOpenAISTTProvider({
+  apiKey: process.env.OPENAI_API_KEY!,
+  defaultLanguage: "en"
+});
+
+export async function POST(request: NextRequest) {
+  const formData = await request.formData();
+  const audioFile = formData.get('audio') as File;
+  const language = formData.get('language') as string | undefined;
+  
+  const audioBlob = new Blob([await audioFile.arrayBuffer()]);
+  const transcription = await provider.transcribe(audioBlob, { language });
+  
+  return NextResponse.json({ transcription });
+}
+```
+
+### Client (uses Remote Transcriber)
+
+```typescript
+import { createRemoteSTTTranscriber } from "@charivo/stt-transcriber-remote";
+import { createSTTManager } from "@charivo/stt-core";
+
+const transcriber = createRemoteSTTTranscriber({
+  apiEndpoint: "/api/stt"
+});
+const sttManager = createSTTManager(transcriber);
+
+// Start recording
+await sttManager.start();
+
+// Stop and get transcription
+const text = await sttManager.stop();
+console.log("User said:", text);
+```
+
+## Pricing (OpenAI Whisper)
+
+- **whisper-1**: $0.006 per minute (rounded to the nearest second)
+
+Example: 30 seconds of audio = $0.003
+
+## Audio Format Support
+
+Whisper supports various audio formats:
+- MP3
+- MP4
+- MPEG
+- MPGA
+- M4A
+- WAV
+- WEBM
+
+Maximum file size: 25 MB
+
+## Performance Tips
+
+1. **Use appropriate audio quality**: Higher quality doesn't always mean better transcription
+2. **Specify language**: Improves accuracy and speed
+3. **Reduce background noise**: Pre-process audio for better results
+4. **Chunk long audio**: Split audio files > 10 minutes for faster processing
+
+## Related Packages
+
+- [`@charivo/stt-transcriber-remote`](../stt-transcriber-remote) - Client-side HTTP STT transcriber (recommended)
+- [`@charivo/stt-transcriber-openai`](../stt-transcriber-openai) - Client-side OpenAI transcriber (testing only)
+- [`@charivo/stt-core`](../stt-core) - STT core functionality
+
+## License
+
+MIT

package/dist/index.d.mts

@@ -0,0 +1,22 @@
+import { STTProvider, STTOptions } from '@charivo/core';
+
+interface OpenAISTTConfig {
+    apiKey: string;
+    defaultModel?: "whisper-1";
+    defaultLanguage?: string;
+    /**
+     * Allow usage in browser (dangerous - exposes API key)
+     * Only use for testing/development
+     */
+    dangerouslyAllowBrowser?: boolean;
+}
+declare class OpenAISTTProvider implements STTProvider {
+    private openai;
+    private defaultModel;
+    private defaultLanguage?;
+    constructor(config: OpenAISTTConfig);
+    transcribe(audio: Blob | ArrayBuffer, options?: STTOptions): Promise<string>;
+}
+declare function createOpenAISTTProvider(config: OpenAISTTConfig): OpenAISTTProvider;
+
+export { type OpenAISTTConfig, OpenAISTTProvider, createOpenAISTTProvider };

package/dist/index.d.ts

@@ -0,0 +1,22 @@
+import { STTProvider, STTOptions } from '@charivo/core';
+
+interface OpenAISTTConfig {
+    apiKey: string;
+    defaultModel?: "whisper-1";
+    defaultLanguage?: string;
+    /**
+     * Allow usage in browser (dangerous - exposes API key)
+     * Only use for testing/development
+     */
+    dangerouslyAllowBrowser?: boolean;
+}
+declare class OpenAISTTProvider implements STTProvider {
+    private openai;
+    private defaultModel;
+    private defaultLanguage?;
+    constructor(config: OpenAISTTConfig);
+    transcribe(audio: Blob | ArrayBuffer, options?: STTOptions): Promise<string>;
+}
+declare function createOpenAISTTProvider(config: OpenAISTTConfig): OpenAISTTProvider;
+
+export { type OpenAISTTConfig, OpenAISTTProvider, createOpenAISTTProvider };

package/dist/index.js

@@ -0,0 +1,75 @@
+"use strict";
+var __create = Object.create;
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __getProtoOf = Object.getPrototypeOf;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __export = (target, all) => {
+  for (var name in all)
+    __defProp(target, name, { get: all[name], enumerable: true });
+};
+var __copyProps = (to, from, except, desc) => {
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (let key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(to, key) && key !== except)
+        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
+  }
+  return to;
+};
+var __toESM = (mod, isNodeMode, target) => (target = mod != null ? __create(__getProtoOf(mod)) : {}, __copyProps(
+  // If the importer is in node compatibility mode or this is not an ESM
+  // file that has been converted to a CommonJS file using a Babel-
+  // compatible transform (i.e. "__esModule" has not been set), then set
+  // "default" to the CommonJS "module.exports" for node compatibility.
+  isNodeMode || !mod || !mod.__esModule ? __defProp(target, "default", { value: mod, enumerable: true }) : target,
+  mod
+));
+var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
+
+// src/index.ts
+var index_exports = {};
+__export(index_exports, {
+  OpenAISTTProvider: () => OpenAISTTProvider,
+  createOpenAISTTProvider: () => createOpenAISTTProvider
+});
+module.exports = __toCommonJS(index_exports);
+var import_openai = __toESM(require("openai"));
+var OpenAISTTProvider = class {
+  openai;
+  defaultModel;
+  defaultLanguage;
+  constructor(config) {
+    if (typeof window !== "undefined" && !config.dangerouslyAllowBrowser) {
+      throw new Error(
+        "OpenAI provider is for server-side use only. Set dangerouslyAllowBrowser: true for testing"
+      );
+    }
+    this.openai = new import_openai.default({
+      apiKey: config.apiKey,
+      dangerouslyAllowBrowser: config.dangerouslyAllowBrowser
+    });
+    this.defaultModel = config.defaultModel || "whisper-1";
+    this.defaultLanguage = config.defaultLanguage;
+  }
+  async transcribe(audio, options) {
+    const audioBlob = audio instanceof Blob ? audio : new Blob([audio], { type: "audio/wav" });
+    const audioFile = new File([audioBlob], "audio.wav", {
+      type: "audio/wav"
+    });
+    const response = await this.openai.audio.transcriptions.create({
+      file: audioFile,
+      model: this.defaultModel,
+      language: options?.language || this.defaultLanguage
+    });
+    return response.text;
+  }
+};
+function createOpenAISTTProvider(config) {
+  return new OpenAISTTProvider(config);
+}
+// Annotate the CommonJS export names for ESM import in node:
+0 && (module.exports = {
+  OpenAISTTProvider,
+  createOpenAISTTProvider
+});

package/dist/index.mjs

@@ -0,0 +1,39 @@
+// src/index.ts
+import OpenAI from "openai";
+var OpenAISTTProvider = class {
+  openai;
+  defaultModel;
+  defaultLanguage;
+  constructor(config) {
+    if (typeof window !== "undefined" && !config.dangerouslyAllowBrowser) {
+      throw new Error(
+        "OpenAI provider is for server-side use only. Set dangerouslyAllowBrowser: true for testing"
+      );
+    }
+    this.openai = new OpenAI({
+      apiKey: config.apiKey,
+      dangerouslyAllowBrowser: config.dangerouslyAllowBrowser
+    });
+    this.defaultModel = config.defaultModel || "whisper-1";
+    this.defaultLanguage = config.defaultLanguage;
+  }
+  async transcribe(audio, options) {
+    const audioBlob = audio instanceof Blob ? audio : new Blob([audio], { type: "audio/wav" });
+    const audioFile = new File([audioBlob], "audio.wav", {
+      type: "audio/wav"
+    });
+    const response = await this.openai.audio.transcriptions.create({
+      file: audioFile,
+      model: this.defaultModel,
+      language: options?.language || this.defaultLanguage
+    });
+    return response.text;
+  }
+};
+function createOpenAISTTProvider(config) {
+  return new OpenAISTTProvider(config);
+}
+export {
+  OpenAISTTProvider,
+  createOpenAISTTProvider
+};

package/package.json

@@ -0,0 +1,40 @@
+{
+  "name": "@charivo/stt-provider-openai",
+  "version": "0.0.1",
+  "description": "OpenAI STT provider for Charivo (server-side)",
+  "main": "dist/index.js",
+  "types": "dist/index.d.ts",
+  "dependencies": {
+    "openai": "^4.47.1",
+    "@charivo/core": "0.0.1"
+  },
+  "devDependencies": {
+    "tsup": "^8.0.0",
+    "typescript": "^5.0.0"
+  },
+  "files": [
+    "dist"
+  ],
+  "publishConfig": {
+    "access": "public"
+  },
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/zeikar/charivo.git",
+    "directory": "packages/stt-provider-openai"
+  },
+  "author": {
+    "name": "Zeikar",
+    "url": "https://github.com/zeikar"
+  },
+  "homepage": "https://github.com/zeikar/charivo#readme",
+  "bugs": {
+    "url": "https://github.com/zeikar/charivo/issues"
+  },
+  "scripts": {
+    "build": "tsup",
+    "dev": "tsup --watch",
+    "clean": "rm -rf dist"
+  }
+}