Agent SkillsAgent Skills
jeremylongshore

deepgram-data-handling

@jeremylongshore/deepgram-data-handling
jeremylongshore
1,761
231 forks
Updated 3/31/2026
View on GitHub

Implement audio data handling best practices for Deepgram integrations. Use when managing audio file storage, implementing data retention, or ensuring GDPR/HIPAA compliance for transcription data. Trigger: "deepgram data", "audio storage", "transcription data", "deepgram GDPR", "deepgram HIPAA", "deepgram privacy", "PII redaction".

Installation

$npx agent-skills-cli install @jeremylongshore/deepgram-data-handling
Claude Code
Cursor
Copilot
Codex
Antigravity

Details

Pathplugins/saas-packs/deepgram-pack/skills/deepgram-data-handling/SKILL.md
Branchmain
Scoped Name@jeremylongshore/deepgram-data-handling

Usage

After installing, this skill will be available to your AI coding assistant.

Verify installation:

npx agent-skills-cli list

Skill Instructions


name: deepgram-data-handling description: | Implement audio data handling best practices for Deepgram integrations. Use when managing audio file storage, implementing data retention, or ensuring GDPR/HIPAA compliance for transcription data. Trigger: "deepgram data", "audio storage", "transcription data", "deepgram GDPR", "deepgram HIPAA", "deepgram privacy", "PII redaction". allowed-tools: Read, Write, Edit, Bash(aws:), Bash(gcloud:) version: 1.0.0 license: MIT author: Jeremy Longshore jeremy@intentsolutions.io compatible-with: claude-code, codex, openclaw tags: [saas, deepgram, data, compliance, privacy]


Deepgram Data Handling

Overview

Best practices for handling audio and transcript data with Deepgram. Covers Deepgram's built-in redact parameter for PII, secure audio upload with encryption, transcript storage patterns, data retention policies, and GDPR/HIPAA compliance workflows.

Data Privacy Quick Reference

Deepgram FeatureWhat It DoesEnable
redact: ['pci']Masks credit card numbers in transcriptQuery param
redact: ['ssn']Masks Social Security numbersQuery param
redact: ['numbers']Masks all numeric sequencesQuery param
Data retentionDeepgram does NOT store audio or transcriptsDefault behavior

Deepgram's data policy: Audio is processed in real-time and not stored. Transcripts are not retained unless you use Deepgram's optional storage features.

Instructions

Step 1: Deepgram Built-in PII Redaction

import { createClient } from '@deepgram/sdk';

const deepgram = createClient(process.env.DEEPGRAM_API_KEY!);

// Deepgram redacts PII directly during transcription
const { result } = await deepgram.listen.prerecorded.transcribeUrl(
  { url: audioUrl },
  {
    model: 'nova-3',
    smart_format: true,
    redact: ['pci', 'ssn'],  // Credit cards + SSNs -> [REDACTED]
  }
);

// Output: "My card is [REDACTED] and SSN is [REDACTED]"
console.log(result.results.channels[0].alternatives[0].transcript);

// For maximum privacy, redact all numbers:
// redact: ['pci', 'ssn', 'numbers']

Step 2: Application-Level PII Redaction

// Additional redaction patterns beyond Deepgram's built-in
const piiPatterns: Array<{ name: string; pattern: RegExp; replacement: string }> = [
  { name: 'email',    pattern: /\b[\w.-]+@[\w.-]+\.\w{2,}\b/g, replacement: '[EMAIL]' },
  { name: 'phone',    pattern: /\b(\+?\d{1,3}[-.\s]?)?\(?\d{3}\)?[-.\s]?\d{3}[-.\s]?\d{4}\b/g, replacement: '[PHONE]' },
  { name: 'dob',      pattern: /\b(0[1-9]|1[0-2])[\/.-](0[1-9]|[12]\d|3[01])[\/.-](19|20)\d{2}\b/g, replacement: '[DOB]' },
  { name: 'address',  pattern: /\b\d{1,5}\s[\w\s]+(?:Street|St|Avenue|Ave|Road|Rd|Drive|Dr|Lane|Ln|Boulevard|Blvd)\b/gi, replacement: '[ADDRESS]' },
];

function redactPII(text: string): { redacted: string; found: string[] } {
  let redacted = text;
  const found: string[] = [];

  for (const { name, pattern, replacement } of piiPatterns) {
    const matches = text.match(pattern);
    if (matches) {
      found.push(`${name}: ${matches.length} occurrence(s)`);
      redacted = redacted.replace(pattern, replacement);
    }
  }

  return { redacted, found };
}

// Usage after Deepgram transcription:
const transcript = result.results.channels[0].alternatives[0].transcript;
const { redacted, found } = redactPII(transcript);
if (found.length > 0) console.log('PII found and redacted:', found);

Step 3: Secure Audio Upload and Storage

import { S3Client, PutObjectCommand, GetObjectCommand } from '@aws-sdk/client-s3';
import { getSignedUrl } from '@aws-sdk/s3-request-presigner';
import { createHash, randomUUID } from 'crypto';
import { readFileSync } from 'fs';

const s3 = new S3Client({ region: process.env.AWS_REGION ?? 'us-east-1' });
const BUCKET = process.env.AUDIO_BUCKET!;

async function uploadAudio(filePath: string, metadata: Record<string, string> = {}) {
  const audio = readFileSync(filePath);
  const checksum = createHash('sha256').update(audio).digest('hex');
  const key = `audio/${randomUUID()}-${checksum.substring(0, 8)}.wav`;

  await s3.send(new PutObjectCommand({
    Bucket: BUCKET,
    Key: key,
    Body: audio,
    ContentType: 'audio/wav',
    ServerSideEncryption: 'aws:kms',  // Encrypt at rest
    Metadata: {
      ...metadata,
      checksum,
      uploadedAt: new Date().toISOString(),
    },
  }));

  // Generate presigned URL for Deepgram to fetch (expires in 1 hour)
  const presignedUrl = await getSignedUrl(s3,
    new GetObjectCommand({ Bucket: BUCKET, Key: key }),
    { expiresIn: 3600 }
  );

  return { key, checksum, presignedUrl };
}

// Upload -> Get presigned URL -> Send to Deepgram
const { presignedUrl } = await uploadAudio('./recording.wav', { source: 'call-center' });
const { result } = await deepgram.listen.prerecorded.transcribeUrl(
  { url: presignedUrl },
  { model: 'nova-3', smart_format: true, redact: ['pci', 'ssn'] }
);

Step 4: Transcript Storage Pattern

interface StoredTranscript {
  id: string;
  audioKey: string;           // S3 reference
  requestId: string;          // Deepgram request_id
  transcript: string;         // Redacted text
  confidence: number;
  duration: number;           // Audio duration in seconds
  model: string;
  speakers: number;
  utterances?: Array<{
    speaker: number;
    text: string;
    start: number;
    end: number;
  }>;
  metadata: {
    redacted: boolean;
    piiTypesFound: string[];
    createdAt: string;
    retentionPolicy: 'standard' | 'legal_hold' | 'hipaa';
    expiresAt: string;
  };
}

function buildTranscriptRecord(
  audioKey: string,
  result: any,
  retentionDays = 90
): StoredTranscript {
  const alt = result.results.channels[0].alternatives[0];
  const { redacted, found } = redactPII(alt.transcript);

  return {
    id: randomUUID(),
    audioKey,
    requestId: result.metadata.request_id,
    transcript: redacted,
    confidence: alt.confidence,
    duration: result.metadata.duration,
    model: Object.keys(result.metadata.model_info ?? {})[0] ?? 'unknown',
    speakers: new Set(alt.words?.map((w: any) => w.speaker).filter(Boolean)).size,
    utterances: result.results.utterances?.map((u: any) => ({
      speaker: u.speaker,
      text: u.transcript,
      start: u.start,
      end: u.end,
    })),
    metadata: {
      redacted: found.length > 0,
      piiTypesFound: found,
      createdAt: new Date().toISOString(),
      retentionPolicy: 'standard',
      expiresAt: new Date(Date.now() + retentionDays * 86400000).toISOString(),
    },
  };
}

Step 5: Data Retention Policies

const retentionPolicies = {
  standard: { days: 90, description: 'Default retention' },
  legal_hold: { days: 2555, description: '7 years for legal' },
  hipaa: { days: 2190, description: '6 years per HIPAA' },
  temp: { days: 7, description: 'Temporary processing' },
};

async function enforceRetention(db: any, s3Client: S3Client, bucket: string) {
  const now = new Date();

  // Find expired transcripts
  const expired = await db.query(
    'SELECT id, audio_key FROM transcripts WHERE expires_at < $1 AND retention_policy != $2',
    [now.toISOString(), 'legal_hold']
  );

  console.log(`Found ${expired.rows.length} expired transcripts`);

  for (const row of expired.rows) {
    // Delete audio from S3
    try {
      await s3Client.send(new DeleteObjectCommand({
        Bucket: bucket, Key: row.audio_key,
      }));
    } catch (err: any) {
      console.error(`S3 delete failed for ${row.audio_key}:`, err.message);
    }

    // Delete transcript from database
    await db.query('DELETE FROM transcripts WHERE id = $1', [row.id]);
    console.log(`Deleted: ${row.id}`);
  }

  return expired.rows.length;
}

Step 6: GDPR Right to Erasure

async function processErasureRequest(userId: string, db: any, s3Client: S3Client, bucket: string) {
  console.log(`Processing GDPR erasure request for user: ${userId}`);

  // 1. Find all user transcripts
  const transcripts = await db.query(
    'SELECT id, audio_key FROM transcripts WHERE user_id = $1', [userId]
  );

  // 2. Delete audio files from S3
  for (const row of transcripts.rows) {
    if (row.audio_key) {
      await s3Client.send(new DeleteObjectCommand({ Bucket: bucket, Key: row.audio_key }));
    }
  }

  // 3. Delete transcripts from database
  const deleted = await db.query('DELETE FROM transcripts WHERE user_id = $1', [userId]);

  // 4. Delete user metadata
  await db.query('DELETE FROM user_metadata WHERE user_id = $1', [userId]);

  // 5. Audit log (keep for compliance — does not contain PII)
  console.log(JSON.stringify({
    action: 'gdpr_erasure',
    userId: userId.substring(0, 8) + '...',  // Partial for audit
    transcriptsDeleted: deleted.rowCount,
    audioFilesDeleted: transcripts.rows.length,
    timestamp: new Date().toISOString(),
  }));

  return { transcriptsDeleted: deleted.rowCount, audioFilesDeleted: transcripts.rows.length };
}

Output

  • Deepgram built-in PII redaction (pci, ssn, numbers)
  • Application-level PII redaction (email, phone, DOB, address)
  • Secure audio upload to S3 with KMS encryption
  • Transcript storage pattern with retention metadata
  • Automated retention enforcement
  • GDPR erasure workflow

Error Handling

IssueCauseSolution
PII still visibleDeepgram redact not setAdd redact: ['pci', 'ssn'] to options
S3 upload failsMissing KMS permissionsAdd kms:GenerateDataKey to IAM role
Retention not enforcedCron not runningSchedule retention job, add monitoring
Erasure incompleteTransaction failedUse database transactions for atomic delete

Resources

More by jeremylongshore

View all
vertex-agent-builder
1,768

Build and deploy production-ready generative AI agents using Vertex AI, Gemini models, and Google Cloud infrastructure with RAG, function calling, and multi-modal capabilities. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

gcp-examples-expert
1,768

Generate production-ready Google Cloud code examples from official repositories including ADK samples, Genkit templates, Vertex AI notebooks, and Gemini patterns. Use when asked to "show ADK example" or "provide GCP starter kit". Trigger with relevant phrases based on skill purpose.

genkit-production-expert
1,768

Build production Firebase Genkit applications including RAG systems, multi-step flows, and tool calling for Node.js/Python/Go. Deploy to Firebase Functions or Cloud Run with AI monitoring. Use when asked to "create genkit flow" or "implement RAG". Trigger with relevant phrases based on skill purpose.

validator-expert
1,768

Validate production readiness of Vertex AI Agent Engine deployments across security, monitoring, performance, compliance, and best practices. Generates weighted scores (0-100%) with actionable remediation plans. Use when asked to validate a deployment, run a production readiness check, audit security posture, or verify compliance for Vertex AI agents. Trigger with "validate deployment", "production readiness", "security audit", "compliance check", "is this agent ready for prod", "check my ADK agent", "review before deploy", or "production readiness check". Make sure to use this skill whenever validating ADK agents for Agent Engine.