Deepgram Core Workflow A: Pre-recorded Transcription
Overview
Production pre-recorded transcription service using Deepgram's REST API. Covers transcribeUrl and transcribeFile, speaker diarization, audio intelligence (summarization, topic detection, sentiment, intent), batch processing with concurrency control, and callback-based async transcription for large files.
Prerequisites
@deepgram/sdk installed, DEEPGRAM_API_KEY configured- Audio files: WAV, MP3, FLAC, OGG, M4A, or WebM
- For batch:
p-limit package (npm install p-limit)
Instructions
Step 1: Transcription Service Class
import { createClient, DeepgramClient } from '@deepgram/sdk';
import { readFileSync } from 'fs';
interface TranscribeOptions {
model?: 'nova-3' | 'nova-2' | 'nova-2-meeting' | 'nova-2-phonecall' | 'base';
language?: string;
diarize?: boolean;
utterances?: boolean;
paragraphs?: boolean;
smart_format?: boolean;
summarize?: boolean; // Audio intelligence
detect_topics?: boolean; // Topic detection
sentiment?: boolean; // Sentiment analysis
intents?: boolean; // Intent recognition
keywords?: string[]; // Keyword boosting: ["term:weight"]
callback?: string; // Async callback URL
}
class DeepgramTranscriber {
private client: DeepgramClient;
constructor(apiKey: string) {
this.client = createClient(apiKey);
}
async transcribeUrl(url: string, opts: TranscribeOptions = {}) {
const { result, error } = await this.client.listen.prerecorded.transcribeUrl(
{ url },
{
model: opts.model ?? 'nova-3',
language: opts.language ?? 'en',
smart_format: opts.smart_format ?? true,
diarize: opts.diarize ?? false,
utterances: opts.utterances ?? false,
paragraphs: opts.paragraphs ?? false,
summarize: opts.summarize ? 'v2' : undefined,
detect_topics: opts.detect_topics ?? false,
sentiment: opts.sentiment ?? false,
intents: opts.intents ?? false,
keywords: opts.keywords,
callback: opts.callback,
}
);
if (error) throw new Error(`Transcription failed: ${error.message}`);
return result;
}
async transcribeFile(filePath: string, opts: TranscribeOptions = {}) {
const audio = readFileSync(filePath);
const mimetype = this.detectMimetype(filePath);
const { result, error } = await this.client.listen.prerecorded.transcribeFile(
audio,
{
model: opts.model ?? 'nova-3',
smart_format: opts.smart_format ?? true,
mimetype,
diarize: opts.diarize ?? false,
utterances: opts.utterances ?? false,
summarize: opts.summarize ? 'v2' : undefined,
detect_topics: opts.detect_topics ?? false,
sentiment: opts.sentiment ?? false,
}
);
if (error) throw new Error(`File transcription failed: ${error.message}`);
return result;
}
private detectMimetype(path: string): string {
const ext = path.split('.').pop()?.toLowerCase();
const map: Record<string, string> = {
wav: 'audio/wav', mp3: 'audio/mpeg', flac: 'audio/flac',
ogg: 'audio/ogg', m4a: 'audio/mp4', webm: 'audio/webm',
};
return map[ext ?? ''] ?? 'audio/wav';
}
}
