Technical specifications

Everything technical teams need to evaluate IdentityCall: file formats, API capabilities, integration methods, security, and compliance.

Audio & file support

Specification	Details
Supported formats	MP3, WAV, M4A, FLAC, OGG, WebM, MP4 (audio extracted)
Maximum file size	2 GB per file
Minimum audio length	Any length for transcription; 3+ seconds for voice biometrics
Sample rate	8kHz – 48kHz (16kHz+ recommended for optimal accuracy)
Channels	Mono and stereo supported; stereo channels processed independently
Encoding	Automatic format detection and conversion; no pre-processing required

Supported languages (50+)

Arabic
Dutch
Hindi
Polish
Bengali
English
Hungarian
Portuguese
Bulgarian
Filipino
Indonesian
Romanian
Catalan
Finnish
Italian
Russian
Chinese (Mandarin)
French
Japanese
Slovak
Chinese (Cantonese)
German
Korean
Spanish
Croatian
Greek
Malay
Swedish
Czech
Gujarati
Norwegian
Tamil
Danish
Hebrew
Persian
Turkish, Ukrainian, + more

API reference

RESTful API with JSON responses. All endpoints require authentication and return consistent error formats.

Authentication

Type	Bearer token authentication
Header	Authorization: Bearer <YOUR_API_KEY>
Key management	Generate and revoke keys from dashboard
Scopes	Keys can be scoped to specific projects or full account access

Core endpoints

POST /api/v1/public/recordings	Upload audio file for processing
GET /api/v1/public/recordings/{id}	Retrieve recording status and metadata
GET /api/v1/public/recordings/{id}/transcription	Get full transcript with speaker diarization
GET /api/v1/public/recordings/{id}/results	Goal scores, categories, extracted fields, speaker identification
GET /api/v1/public/recordings/{id}/summary	AI-generated summary of the call
GET /api/v1/public/projects	List and manage projects
GET /api/v1/public/operators	Manage operators (agents)
GET /api/v1/public/virtual_numbers/available	Browse purchasable phone numbers
POST /api/v1/public/virtual_numbers/purchase	Purchase a phone number

Webhooks

recording.analyzed

Fired when processing completes - transcription, scoring, and analysis done. Payload includes the sections you enable: metadata, summary, transcription, goals, categories, extracted data.

Response format

								{
  "data": {},
  "meta": {
    "request_id": "req_abc123",
    "processing_time_ms": 1250
  }
}

Response format

								{
  "error": {
    "code": "invalid_audio_format",
    "message": "Unsupported file format. See documentation for supported formats.",
    "request_id": "req_abc123"
  }
}

Rate limits

Plan	Limit
Starter	Varies by plan - see pricing
Professional	Higher limits with burst allowance
Enterprise	Custom limits available

Integration methods

Multiple ways to connect IdentityCall to your existing infrastructure. Choose based on your use case and technical requirements.

File upload API

Best for

Batch processing, historical analysis, recordings from any source

How it works

POST audio files to /api/v1/public/recordings. Receive webhook or poll for results.

Formats

All supported audio formats up to 2GB

Processing

Asynchronous - upload returns immediately, results delivered via webhook

Virtual numbers (Live Tracking)

Best for

Real-time call tracking, marketing attribution, inbound call centers

How it works

Provision numbers via API or dashboard. Calls are recorded and processed automatically.

Number types

Local and toll-free numbers available

Features

Greetings, call routing, real-time webhooks, source attribution

SFTP intake

Best for

Existing PBX systems, contact centers, and recorders that export audio files

How it works

Your system drops recordings into a dedicated SFTP folder; IdentityCall imports and processes them automatically

Requirements

Any system that can export recordings over SFTP

Configuration

SFTP credentials provisioned in the dashboard

Direct integrations

HubSpot

Native integration - call data flows to contact timeline

Salesforce

Coming soon - sync transcripts, profiles, and analytics to records

Pipedrive

Coming soon - call outcomes and summaries on your deals

Slack

Notifications and summaries to channels

Telnyx

Powers virtual numbers - provisioning, recording, and webhooks

Custom Integration

Webhooks

Real-time event notifications to your endpoints

REST API

Full programmatic access to all features

Export formats

JSON, CSV for transcripts and analytics

Scheduled reports

Email report delivery on a weekly or monthly schedule

Security & compliance

Enterprise-grade security with compliance frameworks for regulated industries.

Certifications & standards

ISO 27001	Certified - information security management system
GDPR	Compliant - EU data protection regulation
CCPA	Compliant - California Consumer Privacy Act
HIPAA	Available as add-on for healthcare customers

Encryption

In transit	TLS 1.3 for all API and web traffic
At rest	AES-256 encryption for stored data
Key management	Keys managed via secure key management service

Infrastructure

Hosting	Dedicated EU data centers (Hetzner, Finland)
Architecture	Private-network database isolation, Docker workloads
Monitoring	24/7 automated monitoring and alerting
Backups	Automated daily backups with point-in-time recovery

Access control

Authentication	Email/password with MFA support, Google OAuth 2.0
Role-based access (RBAC)	Owner, Admin, Member roles with granular permissions
API key scoping	Keys can be restricted to specific projects
Audit logs	All access and changes logged with timestamps

Voice data security

Voice embeddings	Stored as 256-dimensional vectors - cannot be reversed to recreate audio
Audio retention	Configurable per project; voice embeddings can be retained after audio is deleted
Data deletion	Full deletion on request; embeddings can be removed independently

Compliance features

Data subject requests	API endpoints for access, export, and deletion requests
Consent management	Recording disclosure and consent workflows
Data residency	All customer data hosted in the EU
Processing agreements	DPA available for GDPR compliance

Data handling

Full control over how your data is stored, retained, and exported.

Data retention

Audio recordings	30, 90, 365 days, or indefinite - configurable per project
Transcripts	Follows audio retention or retained independently
Voice embeddings	Can be retained after audio deletion for continued speaker recognition
Analytics & scores	Retained with transcript or exported independently
Audit logs	Retained for compliance period (minimum 1 year)

Data residency

Hosting region	European Union - data centers in Finland
Object storage	Encrypted backups in S3-compatible storage (Cloudflare R2)
Data isolation	Database runs on a private network, unreachable from the public internet

Export options

JSON	Programmatic access, API responses, webhook payloads
CSV	Spreadsheet analysis, BI tool imports
PDF	Human-readable transcript summaries
Raw transcript	Plain text with timestamps

Data deletion

Single recording	Delete via dashboard or API
Voice profile	Remove profile and all associated embeddings
Full project	Delete all recordings, profiles, and analytics
Account closure	All data permanently deleted within 30 days

Additional resources

Full API documentation	/api-docs
Security overview	/security
Pricing & plans	/pricing
Contact sales	/contact

Ready to evaluate?

Start a free trial to test our API with your own audio. Full access, no credit card required.

Start Free Trial Talk to sales