Build Voice
Integrations
In Minutes
Integrate our high-performance speech to text API and conversation intelligence pipeline. Zero-subscription pay-as-you-go billing, built for technical buyers who value speed, accuracy, and developer autonomy.
Developer-Friendly Documentation
Our voice notes API documentation is structured to ensure that junior devs and architects alike can query endpoints in minutes. We support raw audio stream inputs, base64 payload uploads, and handle diarization natively.
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"
}'Pay-As-You-Go Per-Second Billing
Scale seamlessly without monthly subscriptions or upfront lock-ins. Pay only for the exact duration of audio you transcribe.
Connect Transcription Anywhere
Configure Webhooks to automatically push raw transcriptions, AI summaries, and call intelligence data straight to your server endpoints on completion.
Webhook Integration Steps
Register Destination URL
Log in to your dashboard and navigate to Developer Settings. Save your active HTTP POST endpoint (e.g., https://api.yourdomain.com/webhooks/transcription).
Listen for Completion Event
Our worker sends a secure JSON payload with event type "transcription.completed" immediately once your speech processing finishes.
Verify Signing Signatures
VocalNote includes X-VocalNote-Signature in headers. Verify this header using HMAC-SHA256 with your private webhook secret key.
Respond with 200 OK
Acknowledge event receipts by returning an HTTP 200 code within 3 seconds. Failed events are automatically retried up to 5 times.
{
"event": "transcription.completed",
"job_id": "550e8400-e29b-41d4-a716-446655440000",
"status": "completed",
"created_at": "2026-07-14T13:20:00Z",
"result": {
"transcription": "Hello, welcome to VocalNote...",
"rewritten_text": "Welcome to VocalNote...",
"audio_duration_sec": 42.5,
"cost_charged": 0.0118125
},
"metadata": {
"custom_tracking_id": "lead_9812a"
}
}const crypto = require('crypto');
// Verify VocalNote request authenticity
const signature = req.headers['x-vocalnote-signature'];
const rawBody = JSON.stringify(req.body);
const expectedSignature = crypto
.createHmac('sha256', WEBHOOK_SECRET)
.update(rawBody)
.digest('hex');
if (signature === expectedSignature) {
// Safe to process transcription.completed event
res.status(200).send('Verified');
} else {
res.status(401).send('Invalid signature');
}Technical Resources Hub
Deep-dive guides, benchmarks, and tutorials mapped to each step of evaluating and building on the VocalNote speech infrastructure.
Why Your Product Needs a Voice: The Shift to Audio First
Explore the rapid rise of audio interfaces in SaaS products and why outsourcing voice-to-text to a specialized API is a strategic advantage for engineering teams.
- 1.The modern user experience shift: Why speech inputs and voice notes are overtaking keyboard text entry.
- 2.The hidden cost of self-hosting open-source speech models (Whisper, Kaldi) vs API calls.
- 3.Key engineering issues: Noise reduction, overlapping speakers, and diarization accuracy.
- 4.How integrating a high-performance voice transcription API speeds up product launches.
Learn the architectural reasons for using a hosted API. CTA: Get your API developer key.
Ready to Integrate?
Take minutes to set up your keys, read the voice notes API documentation, and integrate. Scale with transparent per-second pay-as-you-go pricing.
