Speech To Text (STT)

Batch Transcribe

Create Batch

POST https://api.lelapa.ai/v1/transcribe/batch

HEADERS

X-CLIENT-TOKEN string required

API token generated for the project.

Code
 
    curl - X 'POST' \
    'https://api.lelapa.ai/v1/transcribe/batch?lang_code=[INSERT-LANGUAGE-CODE]' \
    - H 'X-CLIENT-TOKEN: <INSERT_TOKEN>'

RESPONSE

🟢 201 Created

The request was successful.

RESPONSE example (200)
 
{
     "batch_id": "[BATCH_ID]",
     "blob_endpoint": "[BLOB_ENDPOINT]",
     "sas_token": "[SAS_TOKEN]"
 }

🟠 401 Unauthorized

The client token is missing or invalid.

Upload Files

This will batch upload all files in the current folder ("-s .") to the destination container ("-d .").

Code
 
    az storage blob upload-batch -s . -d .  \
                --blob-endpoint "<blob_endpoint>" \
                --sas-token "<redacted>"

Process Batch

POST https://api.lelapa.ai/api/v1/transcribe/batch/{batch_id}/process?diarise=1&lang_code=[INSERT_LANGUAGE_CODE]

HEADERS

X-CLIENT-TOKEN string required

API token generated for the project.

PARAMS

diairise int optional Boolean value to enable diarisation. Set to 1 to enable diarisation. Set to 0 or remove to disable diarisation.

lang_code string optional

This is the language code that we are going to use to transcribe the uploaded audio.

Optionally, you can specify a language code to specify which model you’re speaking on. The following language codes are valid

Code
 
Afrikaans - "afr"
isiZulu - "zul"
Sesotho - "sot"
South African English - "eng"
African French - "fra"
Code-switched isiZulu (alpha) - "cs-zul"

If no language code is specified, our built-in language ID will select the most probable language.

Code
 
    curl - X 'POST' \
    'https://vulavula-services.lelapa.ai/api/v2alpha/transcribe/batch/{batch_id}/process?diarise=1' \
    - H 'X-CLIENT-TOKEN: [INSERT_TOKEN]'

RESPONSE

🟢 202 Accepted

The request was successful.

🟢 204 No Content

The batch has already been processed.

🟠 401 Unauthorized

The client token is missing or invalid.

Get All Customer Batch Transcriptions

GET https://api.lelapa.ai/v1/transcribe/batch

This endpoint retrieves all batch transcriptions for a customer.

HEADERS

X-CLIENT-TOKEN string required

API token generated for the project.

RESPONSE

🟢 200 OK

The request was successful.

RESPONSE example (200)
 
[
    {
        "id": "[batch_id]",
        "keychain_id": "00000000-0000-0000-0000-000000000000",
        "status": "PROCESSING",
        "language_code": null,
        "created_at": "2025-02-10T09:47:31.716555",
        "updated_at": "2025-02-10T09:50:20.596171"
    },
    {
        "id": "[batch_id]",
        "keychain_id": "00000000-0000-0000-0000-000000000000",
        "status": "COMPLETE",
        "language_code": null,
        "created_at": "2025-02-07T15:57:53.059573",
        "updated_at": "2025-02-07T16:00:42.100059"
    }
]

🟠 401 Unauthorized

The client token is missing or invalid.

Get Batch Transcription Results

GET https://api.lelapa.ai/v1/transcribe/batch/{batch_id}/transcriptions

This endpoint retrieves the transcriptions for a batch.

HEADERS

X-CLIENT-TOKEN string required

API token generated for the project.

PARAMS

batch_id string required

The id of the batch to retrieve transcriptions for.

RESPONSE

🟢 200 OK

The request was successful.

RESPONSE example (200)
 
[
  {
    "id": "5f15e81b-53c2-4c5c-a779-1f6776100543",
    "upload_file_size": null,
    "audio_length_seconds": 20.0,
    "sample_rate": null,
    "channels": null,
    "frame_rate": null,
    "mime_type": null,
    "language_code": "eng",
    "warnings": null,
    "diarisation_result": {
      "timeline": [
        {
          "start_time": 0.0,
          "end_time": 2.14,
          "type": "silence"
        },
        {
          "start_time": 2.14,
          "end_time": 10.54,
          "type": "speech",
          "speaker_id": "speaker0",
          "text": "Thank you so much for calling. You're through to Thandi, how can help you?"
        },
        {
          "start_time": 10.54,
          "end_time": 15.98,
          "type": "speech",
          "speaker_id": "speaker1",
          "text": "Hi, Thandi, I would like to settle my bill for yesterday."
        },
        {
          "start_time": 15.98,
          "end_time": 20.0,
          "type": "music"
        }
      ],
      "words": [
        {
          "word": "Thank",
          "start_time": 2.14,
          "end_time": 2.45,
          "confidence": 0.94,
          "weight": null,
          "word_intensity": null,
          "best_path": true,
          "speaker_id": "speaker0"
        },
        {
          "word": "you",
          "start_time": 2.45,
          "end_time": 2.60,
          "confidence": 0.91,
          "weight": null,
          "word_intensity": null,
          "best_path": true,
          "speaker_id": "speaker0"
        }
        // More words would follow here...
      ]
    },
    "transcription_text": "Thank you so much for calling. You're through to Thandi, how can help you? Hi, Thandi, I would like to settle my bill for yesterday.",
    "transcription_status": "COMPLETED",
    "error_message": null,
    "status_datetime": "2025-04-16T10:45:00Z",
    "upload_datetime": "2025-04-16T10:43:12Z"
  }
]

Code
 
    </div>
</details>
<details>
  <summary>🟠 `401 Unauthorized`</summary>
  <div>
    <div>The client token is missing or invalid.</div>
  </div>
</details>
<details>
  <summary>🟠 `404 Not Found`</summary>
  <div>
    <div>The batch with the given ID does not exist.</div>
  </div>
</details>

## Transcribe Usage Report

`GET` <span href="" style={{"cursor": "none", "pointer-events": "none"}}>https://api.lelapa.ai/v1/transcribe/usage</span>

This endpoint retrieves the usage report for the transcribe service.

HEADERS

**X-CLIENT-TOKEN** _string_ <span style={{"color": "red"}}>required</span>

API token generated for the project.

PARAMS

**start_date_time** _string_ <span style={{"color": "red"}}>required</span>
ISO formatted date string (YYYY-MM-DDTHH:MM:SSZ). The start date of the report.

**end_date_time** _string_ <span style={{"color": "red"}}>required</span>
ISO formatted date string (YYYY-MM-DDTHH:MM:SSZ). The end date of the report.

**interval** _string_ <span style={{"color": "red"}}>required</span>
The interval to group the usage report by. Valid values are `minute`, `hour`, and `day`.

RESPONSE

<details>
  <summary>🟢 `200 OK`</summary>
  <div>
    <div>The request was successful.</div> <br/>
```json title="RESPONSE example (200)"
[
    "usage": [
        {
            "period": "2025-02-16T00:00:00",
            "invocations": 0,
            "successful_invocations": 0,
            "failed_invocations": 0,
            "pending_invocations": 0,
            "seconds_transcribed": 0.0,
            "tokens": 0
        }
    ],
    "total_invocations": 0,
    "total_successful_invocations": 0,
    "total_failed_invocations": 0,
    "total_pending_invocations": 0,
    "total_seconds_transcribed": 0,
    "total_tokens": 0,
    "start_date_time": "2025-02-03T12:00:00+00:00",
    "end_date_time": "2025-02-15T14:00:01+00:00",
    "interval": "day"
}

🟠 401 Unauthorized

The client token is missing or invalid.

🟠 400 Bad request

Invalid date format. Use ISO format (YYYY-MM-DDTHH:MM)

Start date must be before end date

Invalid interval. Use one of: 'minute', 'hour', 'day'

Minute interval only supports a range of 2 hours or less

Hour interval only supports a range of 2 days or less

Day interval only supports a range of 60 days or less

Last modified on November 5, 2025

Sync Transcribe Using SDK