Beta

Simple API. Superpower capabilities.

Security and intelligence for every voice interaction. Deepfake detection, speaker profiling, intent analysis -all in one call.

Early Access

Ask for early access. Start today.

Get your audio intelligence superpowers now. Early access users shape the roadmap, get priority support, and start securing their voice pipelines immediately.

Book a Demo

Capabilities

Beyond deepfake detection -full voice intelligence from a single API.

Liveness Verification

Confirm the speaker is a live human in real time

Live

Deepfake Detection

Identify AI-generated and synthetic speech with confidence scoring

Voice Cloning Detection

Catch cloned voices using formant and prosody analysis

Forensics Traceability

Full audit trail with model version, raw scores, and analytics

Intelligence

Speaker Age Estimation

Beta

Estimate speaker age range from vocal characteristics

Gender Classification

Beta

Classify speaker gender from audio signal

Intent Analysis

Coming Soon

Detect conversational intent -urgency, deception cues, emotional state

Malicious Intent Detection

Coming Soon

Flag social engineering, phishing attempts, and coercion patterns

Emotion Recognition

Coming Soon

Identify anger, stress, fear, and other emotional markers in speech

Language & Accent Detection

Coming Soon

Identify spoken language and regional accent from audio

Speaker Verification

Coming Soon

Verify if two audio samples belong to the same speaker

IVR & Voicebot Detection

Coming Soon

Detect automated voice response systems and distinguish bots from human callers

Noise & Environment Analysis

Coming Soon

Classify background environment and audio quality metrics

Quick Start

cURL
curl -X POST https://api.vocos.io/v1/detect \
  -H "X-API-Key: your-api-key" \
  -F "file=@audio.wav"

# Response:
# {
#   "prediction": "real",
#   "confidence": 0.973,
#   "raw_score": 0.986,
#   "model_version": "forensics-0.3B"
# }

Base URL

https://api.vocos.io

All requests require an X-API-Key header.

Endpoints

POST/v1/detect

Upload an audio file and receive a real/fake verdict with confidence score.

Parameters

fileaudio filerequiredWAV, MP3, FLAC, or OGG. Max 50 MB.
session_idstringGroup multiple segments for sliding-window analysis.

Response

{
  "request_id": "abc-123",
  "prediction": "real",
  "confidence": 0.973,
  "raw_score": 0.986,
  "model_version": "forensics-0.3B"
}
POST/v1/analyze

Full intelligence analysis -deepfake detection plus speaker profiling, age, gender, and environment.

Parameters

fileaudio filerequiredWAV, MP3, FLAC, or OGG. Max 50 MB.
featuresstring[]Features to enable: "age", "gender", "language", "emotion". Defaults to all.

Response

{
  "request_id": "abc-456",
  "security": {
    "prediction": "deepfake",
    "confidence": 0.961,
    "liveness": false
  },
  "intelligence": {
    "age_range": "25-34",
    "gender": "male",
    "language": "en-US",
    "emotion": "neutral",
    "environment": "office"
  },
  "model_version": "forensics-0.3B"
}
GET/v1/health

Check API status, model readiness, and GPU availability.

Response

{
  "status": "healthy",
  "model_loaded": true,
  "device": "cuda",
  "model_version": "forensics-0.3B"
}
POST/v1/chat/stream

Stream a forensic AI analysis of the detection results via Server-Sent Events.

Parameters

session_idstringrequiredSession from a prior /detect call.
messagestringrequiredUser question about the audio.

Response

SSE stream of forensic analysis tokens

Rate Limits

Free

50 requests / day

Pro

10,000 requests / day

Enterprise

Unlimited -custom SLA

Ready to build with voice intelligence?

Ask for early access and get your security audio intelligence superpowers today.