Identity API

Beta: Reach out to the Resemble team to join the preview program.

Create and manage multimodal identity profiles — enrolled from voice samples, face photos, and reference videos — then search incoming media against your known identities.

Identity Types

Voice matching works identically for both types.

Visibility

The Identity Object

1
{
2
  "uuid": "IDENTITY_UUID",
3
  "name": "John Doe",
4
  "identity_type": "person",
5
  "visibility": "team",
6
  "notes": "Executive voice profile",
7
  "voice_profile_id": null,
8
  "created_at": "2026-01-01T00:00:00.000Z",
9
  "updated_at": "2026-01-01T00:00:00.000Z",
10
  "project_count": 1,
11
  "voice_samples": [
12
    { "id": 101, "filename": "sample.wav", "byte_size": 1048576, "content_type": "audio/wav" }
13
  ],
14
  "face_photos": [
15
    { "id": 102, "filename": "headshot.jpg", "byte_size": 204800, "content_type": "image/jpeg" }
16
  ],
17
  "reference_videos": [],
18
  "embeddings": [
19
    { "modality": "voice", "status": "ready", "attachment_count": 1, "computed_at": "2026-01-01T00:00:05.000Z" }
20
  ],
21
  "projects": [
22
    { "uuid": "PROJECT_UUID", "name": "Brand Monitoring" }
23
  ]
24
}

Reference media is held per modality (voice_samples, face_photos, reference_videos) and processed asynchronously — the embeddings array reports each modality’s processing status, and a modality becomes searchable once its embedding status is ready.

Typical Workflow

1. Create an identity — in one call with an audio sample, or as a profile with a chosen type and visibility (Create Identity).
2. Enroll reference media — voice samples, face photos, reference videos (Add Reference Media).
3. Search incoming audio or images against your identities (Search Identities).
4. Delete identities you no longer need (Delete Identity).