> ## Documentation Index
> Fetch the complete documentation index at: https://docs.munsit.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Diarization

> Upload audio and receive diarization segments merged with transcription.

## Endpoint

`POST /audio/diarization/transcribe`

## Authentication

```bash theme={null}
x-api-key: YOUR_MUNSIT_API_KEY
```

## Request

`multipart/form-data`

| Field   | Type   | Required | Description                                                                                       |
| ------- | ------ | -------- | ------------------------------------------------------------------------------------------------- |
| `file`  | file   | Yes      | Audio file in a supported format                                                                  |
| `model` | string | No       | ASR model to use: `munsit` (default) or `munsit-en-ar` (mixed Arabic-English with code-switching) |

## Response

| Field           | Type                                                 | Description                            |
| --------------- | ---------------------------------------------------- | -------------------------------------- |
| `transcription` | object                                               | Transcript and word-level timestamps   |
| `diarization`   | object                                               | Speaker segments with start/end labels |
| `merged`        | array of objects (`start`, `end`, `speaker`, `text`) | Combined diarization + transcript      |
| `duration`      | number                                               | Total duration in seconds              |


## OpenAPI

````yaml POST /audio/diarization/transcribe
openapi: 3.1.0
info:
  title: Munsit API
  description: >-
    Munsit - First True Arabic Voice AI that speaks Dialects From Abu Dhabi to
    Rabat with Voice Cloning & On-prem support
  version: 1.0.0
servers:
  - url: https://api.munsit.com/api/v1
    description: Global production server
  - url: https://ae.api.faseeh.ai/api/v1
    description: UAE regional server
security:
  - apiKeyAuth: []
paths:
  /audio/diarization/transcribe:
    post:
      tags:
        - Speech-to-Text
      summary: Transcribe with Diarization
      description: Upload audio and receive diarization segments merged with transcription.
      operationId: transcribeWithDiarization
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
                - file
              properties:
                file:
                  type: string
                  format: binary
                  description: Audio file for diarization + transcription
                model:
                  type: string
                  enum:
                    - munsit
                    - munsit-en-ar
                  default: munsit
                  description: ASR model to use. Defaults to munsit.
      responses:
        '200':
          description: Diarization transcription created successfully
        '400':
          description: Bad Request
        '401':
          description: Unauthorized - Invalid or missing API key
components:
  securitySchemes:
    apiKeyAuth:
      type: apiKey
      in: header
      name: x-api-key
      description: API key for authentication

````