Whisper X

Overview

The DataCrunch Whisper Inference Service provides access to the Whisper v3 large model endpoint. The endpoint includes advanced options such as WhisperX with diarization, phoneme alignment for word-level timestamps, and subtitle generation in SRT format.

Transcribing Audio

To transcribe audio, submit a request with the audio file URL.

cURL

curl -X POST https://fin-02.inference.datacrunch.io/v1/raw/whisperx/predict \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <your_api_key>" \
  -d \
'{
    "audio_input": "<AUDIO_FILE_URL>"
}'

Python

import requests

url = "https://fin-02.inference.datacrunch.io/v1/raw/whisperx/predict"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer <your_api_key>"
}
data = {
    "audio_input": "<AUDIO_FILE_URL>"
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

JavaScript

const axios = require('axios');

const url = 'https://fin-02.inference.datacrunch.io/v1/raw/whisperx/predict';
const headers = {
  'Content-Type': 'application/json',
  'Authorization': 'Bearer <your_api_key>'
};
const data = {
  audio_input: '<AUDIO_FILE_URL>'
};

axios.post(url, data, { headers: headers })
  .then((response) => {
    console.log(response.data);
  })
  .catch((error) => {
    console.error('Error:', error);
  });

Translating Audio

For translation of the transcribed output to English:

curl -X POST https://fin-02.inference.datacrunch.io/v1/raw/whisperx/predict \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <your_api_key>" \
  -d \
'{
    "audio_input": "<AUDIO_FILE_URL>",
    "translate": true
}'

Generating Subtitles

When creating subtitles it is best to set processing_type="align", to ensure word-level alignment. Omitting the alignment will result in longer subtitle chunks, potentially leading to worse user experience. Setting output="subtitles" ensures that the output is in SRT format.

curl -X POST https://fin-02.inference.datacrunch.io/v1/raw/whisperx/predict \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <your_api_key>" \
  -d \
'{
    "audio_input": "<AUDIO_FILE_URL>",
    "translate": true,
    "processing_type": "align",
    "output": "subtitles"
}'

Performing Speaker Diarization

For speaker diarization (assigning speaker labels to text segments), set processing_type to diarize:

curl -X https://fin-02.inference.datacrunch.io/v1/raw/whisperx/predict \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <your_api_key>" \
  -d \
'{
    "audio_input": "<AUDIO_FILE_URL>",
    "translate": true,
    "processing_type": "diarize"
}'

API Specification

Transcribe, Translate, or Diarize Audio

post

Authorizations

Body

audio_inputstringRequired

URL of the audio file for processing

Example: https://example.com/audiofile.mp3

translatebooleanOptional

Flag to translate the audio content

Default: falseExample: true

languagestringOptionalExample: en

processing_typestringOptionalExample: diarize

outputstringOptionalDefault: rawExample: raw

Responses

200

Successful audio processing response

application/json

Responseany of

or

422

Unprocessable Entity

application/json

500

Internal Server Error

application/json

post

HTTPcURLJavaScriptPython

POST /v1/raw/whisperx/predict HTTP/1.1
Host: fin-02.inference.datacrunch.io
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 127

{
  "audio_input": "https://example.com/audiofile.mp3",
  "translate": true,
  "language": "en",
  "processing_type": "diarize",
  "output": "raw"
}

{
  "usage": {
    "input_audio_length": 0,
    "elapsed_time": 0
  },
  "segments": [
    {
      "start": 1,
      "end": 1,
      "text": "text",
      "words": [
        {
          "word": "text",
          "start": 1,
          "end": 1,
          "score": 1,
          "speaker": "text"
        }
      ]
    }
  ],
  "subtitles": "text"
}

API Parameters

• audio_input (str, required): URL of the audio file. This is a required parameter.

• translate (bool, optional): If enabled, provides the English translation of the output. Defaults to false.

• language (str, optional): Optional two-letter language code to specify the input language for accurate language detection.

• processing_type (str, optional): Defines the processing action. Supported types: diarize, align.

• output (str), optional): Determines the output format. Options: subtitles (in SRT format), raw (time-stamped text). Default is raw.

Copyright notice: WhisperX includes software developed by Max Bain.