![\"360labs.dev\"](\"https://img.shields.io/badge/360labs.dev-Visit%20Website-blue?style=for-the-badge\"){kind=icon}
\n\n\n\n---\n\n## Table of Contents\n\n- [Features](#features)\n- [Installation](#installation)\n- [Quick Start](#quick-start)\n- [Providers](#providers)\n - [Web Speech API](#web-speech-api-browser)\n - [Deepgram](#deepgram)\n - [AssemblyAI](#assemblyai)\n - [Custom Provider](#custom-provider)\n- [Session Management](#session-management)\n- [Events](#events)\n- [Export Formats](#export-formats)\n- [Supported Languages](#supported-languages)\n- [API Reference](#api-reference)\n- [Examples](#examples)\n- [Browser Support](#browser-support)\n- [Contributing](#contributing)\n- [License](#license)\n\n---\n\n## Features\n\n| Feature | Description |\n|---------|-------------|\n| **Multi-Provider Support** | Web Speech API, Deepgram, AssemblyAI, and custom providers |\n| **Real-time Transcription** | Live results with interim and final transcripts |\n| **40+ Languages** | Extensive language support across all providers |\n| **Session Management** | Full control with start, stop, pause, and resume |\n| **Voice Activity Detection** | Automatic speech detection (VAD) |\n| **Audio Recording** | Built-in recording capabilities |\n| **Export Formats** | JSON, Plain Text, SRT, VTT, CSV |\n| **TypeScript First** | Complete type definitions and IntelliSense support |\n| **Event-Driven** | Subscribe to transcription events easily |\n| **Lightweight** | ~200KB package size with zero runtime dependencies |\n| **Cross-Platform** | Works in browsers and Node.js |\n\n---\n\n## Installation\n\n```bash\n# npm\nnpm install @360labs/live-transcribe\n\n# yarn\nyarn add @360labs/live-transcribe\n\n# pnpm\npnpm add @360labs/live-transcribe\n```\n\n---\n\n## Quick Start\n\n### Basic Usage (Web Speech API)\n\n```typescript\nimport { createTranscriber, TranscriptionProvider } from '@360labs/live-transcribe';\n\n// Create a transcriber (Web Speech API - no API key required)\nconst transcriber = createTranscriber({\n provider: TranscriptionProvider.WebSpeechAPI,\n language: 'en-US',\n interimResults: true,\n});\n\n// Listen for transcription results\ntranscriber.on('transcript', (result) => {\n if (result.isFinal) {\n console.log('Final:', result.text);\n } else {\n console.log('Interim:', result.text);\n }\n});\n\n// Handle errors\ntranscriber.on('error', (error) => {\n console.error('Error:', error.message);\n});\n\n// Start transcribing\nawait transcriber.initialize();\nawait transcriber.start();\n\n// Stop when done\nawait transcriber.stop();\n```\n\n### Using Sessions (Recommended)\n\n```typescript\nimport { createSession, TranscriptionProvider } from '@360labs/live-transcribe';\n\n// Create a session for full control\nconst session = createSession({\n provider: TranscriptionProvider.WebSpeechAPI,\n language: 'en-US',\n});\n\n// Access the provider for events\nsession.provider.on('transcript', (result) => {\n console.log(result.text);\n\n // Add to session for later export\n if (result.isFinal) {\n session.addTranscript(result);\n }\n});\n\n// Lifecycle control\nawait session.start();\nsession.pause(); // Pause transcription\nsession.resume(); // Resume transcription\nawait session.stop();\n\n// Get results\nconst transcripts = session.getTranscripts();\nconst fullText = session.getFullText();\nconst stats = session.getStatistics();\n\n// Export in various formats\nconst srtFile = session.export('srt');\nconst jsonFile = session.export('json');\n```\n\n---\n\n## Providers\n\n### Web Speech API (Browser)\n\nThe Web Speech API is built into modern browsers and requires no API key. It's perfect for quick prototypes and applications that don't need cloud-based accuracy.\n\n```typescript\nimport { createTranscriber, TranscriptionProvider } from '@360labs/live-transcribe';\n\nconst transcriber = createTranscriber({\n provider: TranscriptionProvider.WebSpeechAPI,\n language: 'en-US',\n interimResults: true, // Get real-time interim results\n});\n\n// Check browser support\nif (transcriber.isSupported()) {\n await transcriber.initialize();\n await transcriber.start();\n}\n```\n\n**Pros:**\n- No API key required\n- Free to use\n- Works offline (in some browsers)\n- Low latency\n\n**Cons:**\n- Accuracy varies by browser\n- Limited language support compared to cloud providers\n- Requires internet connection in most browsers\n\n---\n\n### Deepgram\n\n[Deepgram](https://deepgram.com) offers high-accuracy, real-time transcription with advanced features like speaker diarization and custom vocabularies.\n\n```typescript\nimport { createTranscriber, TranscriptionProvider } from '@360labs/live-transcribe';\n\nconst transcriber = createTranscriber({\n provider: TranscriptionProvider.Deepgram,\n apiKey: 'your-deepgram-api-key',\n language: 'en-US',\n model: 'nova-2', // Latest model\n punctuate: true, // Auto-punctuation\n interimResults: true,\n});\n\ntranscriber.on('transcript', (result) => {\n console.log(result.text);\n console.log('Confidence:', result.confidence);\n});\n\nawait transcriber.initialize();\nawait transcriber.start();\n```\n\n**Configuration Options:**\n\n| Option | Type | Default | Description |\n|--------|------|---------|-------------|\n| `apiKey` | string | required | Your Deepgram API key |\n| `model` | string | 'nova-2' | Model to use (nova-2, nova, enhanced, base) |\n| `language` | string | 'en-US' | Language code |\n| `punctuate` | boolean | true | Enable auto-punctuation |\n| `interimResults` | boolean | true | Enable interim results |\n| `smartFormat` | boolean | false | Enable smart formatting |\n| `diarize` | boolean | false | Enable speaker diarization |\n\n---\n\n### AssemblyAI\n\n[AssemblyAI](https://assemblyai.com) provides state-of-the-art transcription with features like automatic language detection and content moderation.\n\n```typescript\nimport { createTranscriber, TranscriptionProvider } from '@360labs/live-transcribe';\n\nconst transcriber = createTranscriber({\n provider: TranscriptionProvider.AssemblyAI,\n apiKey: 'your-assemblyai-api-key',\n sampleRate: 16000,\n});\n\ntranscriber.on('transcript', (result) => {\n console.log(result.text);\n});\n\nawait transcriber.initialize();\nawait transcriber.start();\n```\n\n**Configuration Options:**\n\n| Option | Type | Default | Description |\n|--------|------|---------|-------------|\n| `apiKey` | string | required | Your AssemblyAI API key |\n| `sampleRate` | number | 16000 | Audio sample rate in Hz |\n| `wordBoost` | string[] | [] | Words to boost recognition |\n\n---\n\n### Custom Provider\n\nYou can create custom providers by extending the `BaseTranscriber` class:\n\n```typescript\nimport { BaseTranscriber, TranscriptionConfig, SessionState } from '@360labs/live-transcribe';\n\nclass MyCustomProvider extends BaseTranscriber {\n private recognition: any;\n\n constructor(config: TranscriptionConfig) {\n super(config);\n }\n\n isSupported(): boolean {\n return true; // Check if your provider is available\n }\n\n async initialize(): Promise{transcript}
\n{{ transcript }}
\n