Speaker Diarization API - Who Spoke When: Pricing, Documentation

Authentication

All requests require an API key passed via header.

Pricing: Billed at $0.005 per second of input audio — measured on the file you submit. A 10-minute recording costs $3.00. Accepts audio or video; for video the audio is extracted server-side and you are billed on its duration.

Rounding: billing is per second but always rounds up to a whole second — a 5.06-second source bills as 6 seconds. The shortest billable job is 1 second.

Retries: this is an asynchronous job on shared encoding capacity, so a request can occasionally come back processing_failed or take much longer than usual. These are transient and succeed on a retry, and a failed job is never charged — the wallet hold is released. If you chain these tools, retry a failed step rather than failing the whole pipeline.

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

X-Webhook-URL: https://your-server.com/webhook/callback

Request Parameters - Audio Diarize generate request

The result is a JSON file, not audio: media_url points at it and media_type is application/json. It holds ok, speakers and segments — an array of {speaker, start, end} objects with 0-based speaker numbers and float seconds, sorted by start.

speakers is null, not 0, when the run finds no speech at all — music, silence or room tone — and segments is then an empty array. That is a successful, billable result, not an error: treat null as “nobody spoke”. A count is never guessed, so you will not get a phantom single speaker out of an instrumental track.

Request Headers

Response Handling

Common status codes.

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'audio-diarize' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "audio-diarize_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "audio-diarize",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/audio-diarize_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

{
  "request_id": "audio-diarize_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "audio-diarize",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/audio-diarize_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.json"
    ],
    "media_type": "application/json"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Status Values

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

1. Send a generate request to the API endpoint
2. Save the request_id from the response
3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.