VocalNote
Dark Mode
Record New Note

⚡ VocalNote API Referencev1.1

Fast, serverless Edge APIs for Audio Transcription, Documents, Vision OCR, YouTube & Web Summarization

Authentication · Keys

🔐 Authentication Guide

To access the VocalNote API, authenticate your calls by appending a Bearer token inside the Authorization header. You can retrieve and refresh your keys directly from the Developer API Dashboard.

// Security Notice

Never expose secret keys in public code repositories or client-side files. Always run operations in secure back-channel services.

Header Format
Authorization: Bearer vn_your_api_key
Billing · Wallet Rates

💳 Billing Logic & Pricing Rules

VocalNote bills strictly by the second based on the audio processed or text analyzed. Deductions occur in real-time directly from your wallet balance. There are no monthly fees, flat subscriptions, or hidden charges.

All-in-One rate
$1.00 / hr
$0.000278 per second
Single Operation
$0.60 / hr
$0.000167 per second
Behavioral Analysis
$0.30 / hr
$0.000083 per second
  • No rounding up: A 15-second transcription is billed for exactly 15 seconds.
  • Credits expiry: Deposited funds stay active in your account indefinitely and never expire.
  • Auto-Recharge: Top up automatically when your balance drops below the $1 threshold.
  • Cap limits: Set custom monthly caps to prevent unexpected volume spikes.
🎙️ Endpoints · Audio Ingestion

Transcribe / Note Process

Transcribe and rewrite audio files with high accuracy. Send raw base64 audio and select your desired formatting style.

POST/apiv1/process

// Parameters

ParamTypeRequired
audio_base64
Base64 audio string. Max 25 MB.
string✅ Yes
mode
Operation mode: "transcribe", "rewrite", or "combined" (default).
stringNo
style
Clean-up style. Supported values: "Casual", "Professional", "Journal", "List", "Tweet", "Email", "Academic", "Social Media", "Meeting", "Blog Post", "Executive Summaries", "Product Spec", "Agent Prompt", "Audio-to-MIDI", "Audio-to-Sheet Music".
stringNo

// Billing Rates

Combined (Transcribe + Rewrite)$1.00 / hr ($0.000278/sec)
Single (Transcribe OR Rewrite)$0.60 / hr ($0.000167/sec)
curl -X POST https://worker.vocalnote.app/apiv1/process \
  -H "Authorization: Bearer vn_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
  "mode": "combined",
  "audio_base64": "UklGRiQAA...",
  "mime_type": "audio/webm",
  "style": "Professional"
}'
Accepted Response (202)
{
  "success": true,
  "status": "processing",
  "job_id": "550e8400-e29b-41d4-a716-446655440000",
  "message": "Request is processing."
}
🧠 Analytics · Insights

Behavioural Analytics

Analyze conversation logs to detect empathy, soft skills, calculate listener-talk ratios, and scrub PII from transcripts.

POST/apiv1/analyze

// Parameters

ParamTypeRequired
transcript
Raw text transcription to analyze.
string✅ Yes
save_to_vocalnote
Whether to persist analytics results to the dashboard.
booleanNo
metadata
Custom tracking object, e.g. {"call_id": "12345"}
objectNo
scrubbed_transcript
Off by default. Set to true to redact PII (SSN, credit cards).
booleanNo

// Billing Rates

Behavioral Analysis$0.30 / hr ($0.005 / min)
PII Scrubbing$0.005 / request (if requested)
Minimum Charge RuleBilled by estimated duration ($0.000083/sec)
curl -X POST https://worker.vocalnote.app/apiv1/analyze \
  -H "Authorization: Bearer vn_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
  "transcript": "Agent: Hello! Customer: I need help.",
  "save_to_vocalnote": true,
  "metadata": {
    "call_id": "12345"
  },
  "scrubbed_transcript": false
}'
Accepted Response (202)
{
  "success": true,
  "status": "processing",
  "job_id": "776e8400-e29b-41d4-a716-446655440000",
  "message": "Request is processing."
}
📄 Endpoints · Document Processing

Document Summarizer (PDF, Word, Excel, Text)

Extract and summarize text, PDF files, Word (.docx), and Excel spreadsheets into structured notes with key insights.

POST/apiv1/summarize/document

// Parameters

ParamTypeRequired
document_base64
Base64 encoded document file (required for PDF or binary files).
stringNo*
document_text
Raw text/csv extracted from document (required if document_base64 is omitted).
stringNo*
mime_type
MIME type: application/pdf, text/plain, text/csv, etc.
stringNo
file_name
Original file name for context (e.g., quarterly_report.pdf).
stringNo
style
Note style (Casual, Professional, Executive Summaries, List, etc.).
stringNo
language
Target language for the summary and key insights (default: English).
stringNo

// Billing Rates

Document Summarization$0.01 / request
curl -X POST https://worker.vocalnote.app/apiv1/summarize/document \
  -H "Authorization: Bearer vn_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
  "file_name": "financial_report.pdf",
  "mime_type": "application/pdf",
  "document_base64": "JVBERi0xLjQK...",
  "style": "Executive Summaries",
  "language": "English"
}'
Response (200 OK)
{
  "success": true,
  "title": "Q3 Financial Performance & Growth Drivers",
  "summary": "Revenue increased by 28% year-over-year with strong expansion across enterprise accounts.",
  "keyInsights": [
    "Gross margin improved to 74% due to infrastructure optimizations",
    "Net ARR grew from $4.2M to $5.4M in Q3",
    "Customer churn decreased to a record low of 1.2%"
  ],
  "rewrittenText": "### Executive Summary\n\nThe company demonstrated exceptional growth during Q3...",
  "tags": ["Finance", "Q3", "Revenue", "Growth"],
  "transcript": "Total revenue for the three months ended September 30 was...",
  "cost_charged": 0.01,
  "request_id": "880e8400-e29b-41d4-a716-446655440001"
}
🖼️ Endpoints · Vision & OCR

Image Multimodal OCR & Insights

Read whiteboard photos, handwritten notes, infographics, receipts, and screenshots using multimodal AI vision.

POST/apiv1/summarize/image
curl -X POST https://worker.vocalnote.app/apiv1/summarize/image \
  -H "Authorization: Bearer vn_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
  "image_base64": "/9j/4AAQSkZJRgABAQ...",
  "mime_type": "image/jpeg",
  "style": "Meeting",
  "prompt": "Extract all action items and timeline milestones"
}'
Response (200 OK)
{
  "success": true,
  "title": "Architecture Whiteboard & Next Steps",
  "summary": "System design diagram outlining migration from monolith to serverless microservices.",
  "keyInsights": [
    "API Gateway routes incoming auth to Cloudflare Edge",
    "Database cache layer utilizes Redis for <5ms lookups",
    "Sprint target set for full deployment by October 15"
  ],
  "rewrittenText": "## System Architecture Overview\n\nBased on the whiteboard design...",
  "tags": ["Architecture", "SystemDesign", "Whiteboard"],
  "transcript": "[OCR Text: Cloudflare Edge -> API Gateway -> PostgreSQL Primary]",
  "cost_charged": 0.005,
  "request_id": "990e8400-e29b-41d4-a716-446655440002"
}
▶️ Endpoints · Video Intelligence

YouTube Video Summarizer

Extract and summarize any YouTube video or Short into structured notes, timestamped insights, and action items.

POST/apiv1/summarize/youtube
curl -X POST https://worker.vocalnote.app/apiv1/summarize/youtube \
  -H "Authorization: Bearer vn_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
  "youtube_url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
  "style": "List",
  "language": "English"
}'
Response (200 OK)
{
  "success": true,
  "title": "Core Insights from Video Discussion",
  "summary": "Comprehensive overview of the concepts discussed in the video.",
  "keyInsights": [
    "Key breakthrough discussed at 03:20 regarding latency reduction",
    "Model optimizations enabled 4x throughput improvements",
    "Open-source release scheduled for next quarter"
  ],
  "rewrittenText": "### Key Takeaways\n\n- **Breakthrough**: Modern architectures significantly reduce overhead...",
  "tags": ["YouTube", "VideoSummary", "TechTalk"],
  "metadata": {
    "videoId": "dQw4w9WgXcQ",
    "author": "Tech Creator",
    "originalTitle": "Building Scalable AI Systems",
    "thumbnailUrl": "https://img.youtube.com/vi/dQw4w9WgXcQ/hqdefault.jpg"
  },
  "cost_charged": 0.01,
  "request_id": "aa0e8400-e29b-41d4-a716-446655440003"
}
🌐 Endpoints · Web Summarizer

Web Page & Article Summarizer

Scrapes, sanitizes, and summarizes any public article or webpage URL into structured notes with core takeaways.

POST/apiv1/summarize/url
curl -X POST https://worker.vocalnote.app/apiv1/summarize/url \
  -H "Authorization: Bearer vn_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
  "url": "https://example.com/blog/future-of-ai",
  "style": "Professional",
  "language": "English"
}'
Response (200 OK)
{
  "success": true,
  "title": "The Future of Multimodal AI Agents",
  "summary": "An in-depth exploration of how multimodal reasoning transforms knowledge work.",
  "keyInsights": [
    "Multimodal models now ingest video, audio, code, and documents simultaneously",
    "Context window expansions allow entire codebases in active memory",
    "Autonomous sub-agent architectures reduce hallucination rates by 60%"
  ],
  "rewrittenText": "The transition from text-only models to multimodal agentic systems...",
  "tags": ["AI", "Multimodal", "Technology", "Agents"],
  "metadata": {
    "url": "https://example.com/blog/future-of-ai",
    "siteName": "example.com",
    "originalTitle": "The Future of Multimodal AI"
  },
  "cost_charged": 0.005,
  "request_id": "bb0e8400-e29b-41d4-a716-446655440004"
}
🕒 Queue · Status Checks

Job Status Query

Check the processing status of a queued transcription or behavioral analysis job.

GET/apiv1/status/{job_id}

// Parameters

ParamTypeRequired
job_id
The job tracking ID returned from process/analyze response payload.
string✅ Yes

// Billing Rates

Status ChecksFree of charge
curl -X GET https://worker.vocalnote.app/apiv1/status/{job_id} \
  -H "Authorization: Bearer vn_your_api_key"
|
{
  "success": true,
  "status": "completed",
  "result": {
    "transcription": "Verbatim audio text...",
    "rewritten_text": "Polished, styled output...",
    "audio_duration_sec": 42,
    "cost_charged": 0.000011667,
    "request_id": "550e8400-e29b-41d4-a716-446655440000"
  },
  "error": null,
  "created_at": "2024-03-22T12:00:00Z",
  "updated_at": "2024-03-22T12:00:30Z"
}
VocalNote - AI note takerVocalNote on Good AI ToolsVocalNote on VibeRank