Speaker Verification API

Verify if two clips are the same speaker with one API call.

Upload a reference and a candidate audio file with multipart/form-data and receive a same-speaker verdict, similarity score, match threshold, and clip metadata for both files. Built for call authentication, fraud prevention, and access control.

Reference + candidate multipart upload
0-100 similarity score returned
Clear same-speaker verdict
Remaining requests included

Quickstart

POST multipart/form-data
/v1/speaker-verification/apiPOST

// Headers

apiKey:

YOUR_API_KEY

// Form Data

formData.append("reference", referenceAudioFile);
formData.append("candidate", candidateAudioFile);

// Sample Response

{
  "success": true,
  "same_speaker": true,
  "similarity": 87,
  "threshold": 75,
  "reference_audio": {
    "duration": 4.8,
    "sample_rate": 16000
  },
  "candidate_audio": {
    "duration": 5.1,
    "sample_rate": 16000
  },
  "remainingRequests": 119
}

Send both audio files using the reference and candidate fields. Supported formats include WAV, MP3, M4A, FLAC, OGG, WebM, AAC, Opus, WMA, AMR, 3GP, AIFF, AU, and more.

Call center authentication

Confirm a caller's identity against a known voiceprint before granting access to sensitive account actions.

Fraud prevention

Catch impersonation attempts by comparing a new voice sample against a trusted reference recording.

Clean JSON responses

Receive same_speaker, similarity, threshold, reference_audio, candidate_audio, and remainingRequests in one compact response.

Fast integration

A simple dual-field multipart upload flow keeps implementation straightforward in web, backend, and mobile services.

Usage visibility

Track remaining request quota directly in each successful response.

Focused format support

Designed to handle many common voice analysis formats, including WAV, MP3, M4A, FLAC, OGG, WebM, AAC, Opus, WMA, AMR, 3GP, AIFF, AU, and more.

How it works

Speaker verification in three steps.

1

Upload both clips

POST multipart/form-data to the /api endpoint with your apiKey header, a reference field, and a candidate field.

2

Receive JSON

Get the same_speaker verdict, similarity score, match threshold, and audio details for both clips after processing completes.

3

Act on the verdict

Use the result to authenticate a caller, approve a sensitive action, or flag a likely impersonation attempt.

cURL

Multipart upload
curl -X POST 'https://api.genderrecognition.com/v1/speaker-verification/api' \
  -H 'apiKey: YOUR_API_KEY' \
  -F 'reference=@/path/to/reference.wav' \
  -F 'candidate=@/path/to/candidate.wav'

JavaScript

fetch example
const apiKey = "YOUR_API_KEY";
const formData = new FormData();
formData.append("reference", referenceAudioFile);
formData.append("candidate", candidateAudioFile);

const response = await fetch(
  "https://api.genderrecognition.com/v1/speaker-verification/api",
  {
    method: "POST",
    headers: {
      apiKey,
    },
    body: formData,
  }
);

const result = await response.json();

Call center authentication

Verify a caller's identity against an enrolled voiceprint before allowing sensitive account changes.

Voice-based access control

Gate logins, approvals, or physical access behind a voice match before granting entry.

Fraud prevention

Flag mismatched voices on high-risk transactions so reviewers can investigate before funds move.

Ready to Get Started?

We provide the best gender recognition services using advanced AI technology to ensure accuracy and privacy for all users.

Create an account in minutes to claim your API key and have unrestricted access.

Register Account

Daily Free Usage

Enjoy a generous free tier every day to test and explore our APIs.

Try API

Pricing

Simple, transparent pricing. First 1000 requests free, then pay as you go. Check out our pricing page for more details.

View Pricing

Frequently Asked Questions