Speech To Text Endpoint

Overview

Speech-to-Text transforms audio into written transcription, allowing spoken language to be converted into text for various applications.

Request

--request POST 'https://modelslab.com/api/v6/whisper/transcribe' \

Make a POST request to https://modelslab.com/api/v6/whisper/transcribe endpoint and pass the required parameters as a request body.

Body Attributes

Parameter	Description	Values
key	Your API Key used for request authorization	string
audio_url	URL of the audio file to be transcribed.	File (wav, mp3, flac, opus), max duration: From 5 seconds to 300 seconds(5 minutes) string (URL)
input_language	The language code of the audio content.	string (ISO 639-1, e.g., 'en', 'es', 'fr')
timestamp_level	Specifies the level of detail for timestamps in the transcription.	'word', 'sentence', or null (default: null)
webhook	Set a URL to receive a POST API call once the audio generation is complete.	URL
track_id	This ID is returned in the response to the webhook API call. Used to identify the webhook request.	integral value

Input Languages Supported

"Afrikaans": "af",
"Arabic": "ar",
"Belarusian": "be",
"Bengali": "bn",
"Bulgarian": "bg",
"Chinese": "zh",
"Czech": "cs",
"Danish": "da",
"Dutch": "nl",
"English": "en",
"Finnish": "fi",
"French": "fr",
"German": "de",
"Greek": "el",
"Hebrew": "he",
"Hindi": "hi",
"Hungarian": "hu",
"Indonesian": "id",
"Italian": "it",
"Japanese": "ja",
"Kannada": "kn",
"Korean": "ko",
"Malayalam": "ml",
"Marathi": "mr",
"Nepali": "ne",
"Panjabi": "pa",
"Persian": "fa",
"Polish": "pl",
"Portuguese": "pt",
"Romanian": "ro",
"Russian": "ru",
"Serbian": "sr",
"Spanish": "es",
"Swedish": "sv",
"Tagalog": "tl",
"Tamil": "ta",
"Telugu": "te",
"Thai": "th",
"Turkish": "tr",
"Ukrainian": "uk",
"Urdu": "ur",
"Vietnamese": "vi",
"Welsh": "cy"

info

Whisper supports several languages, but performance may vary due to factors like limited training data, script complexity, and regional dialects, potentially affecting transcription accuracy.

Example

Body

Body

{
    "key": "",
    "audio_url": "https://pub-f3505056e06f40d6990886c8e14102b2.r2.dev/audio/tom_hanks_1.wav",
    "input_language": "en",
    "timestamp_level": null,
    "webhook": null,
    "track_id": null
}

Request

JS

var myHeaders = new Headers();
myHeaders.append("Content-Type", "application/json");

var raw = JSON.stringify({
    "key": "",
    "audio_url": "https://pub-f3505056e06f40d6990886c8e14102b2.r2.dev/audio/tom_hanks_1.wav",
    "input_language": "en",
    "timestamp_level": null,
    "webhook": null,
    "track_id": null
});

var requestOptions = {
  method: 'POST',
  headers: myHeaders,
  body: raw,
  redirect: 'follow'
};

fetch("https://modelslab.com/api/v6/whisper/transcribe", requestOptions)
  .then(response => response.text())
  .then(result => console.log(result))
  .catch(error => console.log('error', error));

PHP

<?php

$payload = [
  "key" => "",
  "audio_url" => "https://pub-f3505056e06f40d6990886c8e14102b2.r2.dev/audio/tom_hanks_1.wav",
  "input_language" => "en",
  "timestamp_level" => null,
  "webhook" => null,
  "track_id" => null
];

$curl = curl_init();

curl_setopt_array($curl, array(
  CURLOPT_URL => 'https://modelslab.com/api/v6/whisper/transcribe',
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => '',
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 0,
  CURLOPT_FOLLOWLOCATION => true,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => 'POST',
  CURLOPT_POSTFIELDS => json_encode($payload),
  CURLOPT_HTTPHEADER => array(
    'Content-Type: application/json'
  ),
));

$response = curl_exec($curl);

curl_close($curl);
echo $response;

NODE

var request = require('request');
var options = {
  'method': 'POST',
  'url': 'https://modelslab.com/api/v6/whisper/transcribe',
  'headers': {
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    "key": "",
    "audio_url": "https://pub-f3505056e06f40d6990886c8e14102b2.r2.dev/audio/tom_hanks_1.wav",
    "input_language": "en",
    "timestamp_level": null,
    "webhook": null,
    "track_id": null
  })
};

request(options, function (error, response) {
  if (error) throw new Error(error);
  console.log(response.body);
});

PYTHON

import requests
import json

url = "https://modelslab.com/api/v6/whisper/transcribe"

payload = json.dumps({
    "key": "",
    "audio_url": "https://pub-f3505056e06f40d6990886c8e14102b2.r2.dev/audio/tom_hanks_1.wav",
    "input_language": "en",
    "timestamp_level": null,
    "webhook": None,
    "track_id": None
})

headers = {
  'Content-Type': 'application/json'
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)

JAVA

OkHttpClient client = new OkHttpClient().newBuilder()
  .build();
MediaType mediaType = MediaType.parse("application/json");
RequestBody body = RequestBody.create(mediaType, "{\n    \"key\":\"\",\n    \"audio_url\":\"https://pub-f3505056e06f40d6990886c8e14102b2.r2.dev/audio/tom_hanks_1.wav\",\n    \"input_language\":\"en\",\n    \"timestamp_level\":null,\n    \"webhook\":\"\",\n    \"track_id\":\"\"\n}");
Request request = new Request.Builder()
  .url("https://modelslab.com/api/v6/whisper/transcribe")
  .method("POST", body)
  .addHeader("Content-Type", "application/json")
  .build();
Response response = client.newCall(request).execute();

Response

{
    "status": "success",
    "eta": 5,
    "id": 330711,
    "output": [
        "https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/generations/2966b901-d93a-4b3b-a2f5-db2b6ea081a8.txt"
    ],
    "proxy_links": [
        "https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/generations/2966b901-d93a-4b3b-a2f5-db2b6ea081a8.txt"
    ],
    "meta": {
        "input_language": "en",
        "timestamp_level": null,
        "file_id": "2966b901-d93a-4b3b-a2f5-db2b6ea081a8",
        "duration": 11.311,
        "audio_url": "https://pub-f3505056e06f40d6990886c8e14102b2.r2.dev/audio/tom_hanks_1.wav"
    }
}