# Whisper Diarization

> Whisper transcription with speaker diarization (8M+ runs) — returns who said what with per-segment speaker labels and timestamps. Ideal for meetings and interviews.

- **Provider**: replicate
- **Model ID**: thomasmol/whisper-diarization
- **Category**: speech_to_text
- **Credits**: 7 per request
- **Pricing Type**: fixed

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `language` (string, optional): Language of the spoken words as a language code like 'en'. Leave empty to auto detect language.
- `file_string` (string, optional): Either provide: Base64 encoded audio file,
- `prompt` (string, optional): Vocabulary: provide names, acronyms and loanwords in a list. Use punctuation for best accuracy.
- `file_url` (string, optional): Or provide: A direct audio file URL
- `num_speakers` (integer, optional): Number of speakers, leave empty to autodetect. (Range: min: 1, max: 50)
- `translate` (boolean, optional): Translate the speech into English. (Default: `False`)
- `file` (string, optional): Or an audio file

## Example Request

```json
{
  "model": "thomasmol/whisper-diarization",
  "input": {
    "file_url": "",
    "language": "en",
    "file": "https://replicate.delivery/pbxt/JcL0ttZLlbchC0tL9ZtB20phzeXCSuMm0EJNdLYElgILoZci/AI%20should%20be%20open-sourced.mp3",
    "prompt": "LLama, AI, Meta.",
    "num_speakers": 2,
    "translate": false
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

json

## Tags

speech-to-text, diarization, whisper, meetings, speaker-labels

## Documentation

https://replicate.com/thomasmol/whisper-diarization