Face AI

Tatvora Face Verification AI

Verify whether two faces belong to the same person.

Tatvora Face Verification AI — also available as the Tatvora Face Match API — performs one-to-one comparison. Supply a reference photograph and a live or submitted image, and the API returns whether the two faces belong to the same person along with a similarity score you can threshold against your own risk policy.

POST https://api.tatvora.com/api/v1/face/verify
POST https://api.tatvora.com/api/v1/face/verify
curl -X POST https://api.tatvora.comPOST /api/v1/face/verify \
  -H "Authorization: Bearer $TATVORA_API_KEY" \
  -F "reference_image=@reference.jpg" \
  -F "probe_image=@selfie.jpg"
What this model does — and does not — do Face Verification is one-to-one matching between two supplied images. It is not face detection, and it does not search a candidate set — use Face Recognition for one-to-many identification.
How it works

The Face Verification pipeline

  1. Reference image
  2. Live / user image
  3. Tatvora Face Verification AI
  4. Match / No match
See it work

What you send, and what you get back

A worked example of a single Face Verification AI call, end to end.

POST /api/v1/face/verify

1 · You send two images

Reference photo
on file
Live capture
just now

2 · We process

Tatvora Face Verification AI 1:1 comparison

3 · You receive

MATCH
0.00 similarity 0.94 1.00
Same person Yes
Your threshold 0.80
{
  "success": true,
  "match": true,
  "similarity": 0.94,
  "threshold": 0.80
}

Sample data for illustration. Verification compares only the two images you send; it does not search a candidate set — that is Face Recognition. You choose the threshold at which a score counts as a match.

Capabilities

What Face Verification AI can do

  • Compare two face images directly
  • Similarity scoring between a reference and a probe image
  • One-to-one identity verification
  • Configurable match threshold
  • Reference photo comparison for onboarding and KYC
  • Authentication checks at the point of access
Use cases

Where it is applied

  • Attendance validation against an employee photo
  • Login and step-up authentication
  • Employee verification
  • KYC and customer onboarding
  • Identity confirmation before sensitive actions
  • Account recovery flows
  • Approval workflows requiring a verified approver
API reference

Request and response

Authenticate with a bearer API key over HTTPS. Upload two files as multipart/form-data and receive a JSON response.

Request fields

  • reference_image — file part, multipart/form-data
  • probe_image — file part, multipart/form-data
  • Authorization: Bearer YOUR_API_KEY — required header

Endpoints and payloads shown on this site are illustrative examples of the published interface. Never expose a secret API key in client-side code.

200 OK — example response
{
  "success": true,
  "request_id": "req_b310af52",
  "match": true,
  "similarity": 0.93,
  "threshold_applied": 0.80
}
FAQ

Face Verification AI questions

Face Verification is one-to-one matching. You supply two images — typically a reference photograph and a live capture — and the API returns whether they are the same person, with a similarity score you can threshold. It compares only those two images; to search a candidate set, use Face Recognition.
More AI APIs

Combine Face Verification AI with the rest of the platform

Document AI

Tatvora OCR AI

Turn documents into usable data.

Extract text and structured information from images, scans, PDFs and office documents through a single document intelligence API.

View all AI products

Try Tatvora Face Verification AI

Request an evaluation key and validate the model against your own data before choosing a plan.

Questions? Email support@tatvora.com