Speech To Text (STT)

Fast Transcribe

Transcribe V1 has been deprecated!

The Transcribe V1 endpoint has been deprecated and will be removed in a future release. This documentation has been updated to reference the newer v2alpha API, which includes improvements and ongoing support. If you're still using V1, we recommend migrating to v2alpha as soon as possible to ensure continued functionality. API Reference

POST https://vulavula-services.lelapa.ai/api/v2alpha/transcribe/fast

FORM DATA

upload string of bytes required

String of bytes of the file.

HEADERS

X-CLIENT-TOKEN string required

API token generated for the project.

CONTENT-TYPE string required

Set content-type to multipart/form-data

PARAMS

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

Afrikaans - "afr"
isiZulu - "zul"
Sesotho - "sot"
South African English - "eng"
African French - "fra"

text

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

import requests
    import json
    from pprint import pprint

    # set these

    API_KEY = "<INSERT-TOKEN>"
    WAV_FILE = "<INSERT-PATH-TO-AUDIO>"

    def file_data(path: str):
        with open(path, "rb") as f:
            return f.read()

        url = "https://vulavula-services.lelapa.ai/api/v2alpha/transcribe/fast"

        headers = {
        "X-CLIENT-TOKEN": API_KEY,
        }

        files = {
        'upload': ('fra_colours.wav', file_data(WAV_FILE), 'audio/wav')
        }

        # if language code is known, set it
        params = {
        "lang_code": "<INSERT-LANGUAGE-CODE>"
        }

        resp = requests.post(url, headers=headers, files=files, params=params)

        pprint(resp.json())

python

RESPONSE

🟢 200 OK

The request was successful.

RESPONSE example (200)

{
    "text": "sikubingelele esikomkene ndabenzehoranokqale mini sibingelelenakuwe ska holele ni lotholhlalo zohlakazi at itithi lezindabani",
    "lang_code": "sot"
    "diarisation: {}
}

json

RESPONSE BODY PARAMS

Object
text string required. The transcribed text of the provided audio file.
lang_code string required. The language code representing the detected/provided language of the transcription, in this case, `"sot"` for Sesotho.
diarisation dict required. Diarisation data when available.

🟠 401 Unauthorized

The client token is missing or invalid.

🔴 415 Unsupported Media Type

Not a valid WAV file.

🔴 500 Internal Server Error

An unexpected error occurred on the server.

🔴 503 The request timed out

The request timed out - please try again.

Sync Transcription (file upload)Batch Transcribe

​Fast Transcribe

Fast Transcribe