Langsung ke konten utama

​
Body Permintaan

Timeout permintaan sinkron: endpoint non-chat ini menunggu model yang dirutekan selesai. Input besar, audio panjang, atau batch besar dapat melebihi default client umum 30s, jadi atur timeout HTTP client Anda minimal 120s.
​
file
file
wajib
File audio untuk ditranskripsikan. Format yang didukung: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm.
​
model
string
default:"whisper-1"
Model yang digunakan. Saat ini hanya whisper-1 yang didukung.
​
language
string
Bahasa audio dalam format ISO-639-1 (misalnya, en, zh, ja).
​
prompt
string
Teks opsional untuk memandu gaya model atau melanjutkan segmen sebelumnya.
​
response_format
string
default:"json"
Format output: json, text, srt, verbose_json, vtt.
​
temperature
number
default:"0"
Temperatur sampling (0 hingga 1).
​
timestamp_granularities
array
Granularitas timestamp: word dan/atau segment. Memerlukan verbose_json.

​
Respons

​
text
string
Teks hasil transkripsi.
Untuk verbose_json:
​
task
string
Selalu transcribe.
​
language
string
Bahasa yang terdeteksi.
​
duration
number
Durasi audio dalam detik.
​
segments
array
Segmen transkripsi dengan timestamp.
​
words
array
Timestamp tingkat kata (jika diminta).
curl -X POST "https://api.tokenlab.sh/v1/audio/transcriptions" \
  -H "Authorization: Bearer sk-your-api-key" \
  -F file="@audio.mp3" \
  -F model="whisper-1" \
  -F language="en"

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://api.tokenlab.sh/v1"
)

with open("audio.mp3", "rb") as audio_file:
    response = client.audio.transcriptions.create(
        model="whisper-1",
        file=audio_file,
        language="en"
    )

print(response.text)

import OpenAI from 'openai';
import fs from 'fs';

const client = new OpenAI({
  apiKey: 'sk-your-api-key',
  baseURL: 'https://api.tokenlab.sh/v1'
});

const response = await client.audio.transcriptions.create({
  model: 'whisper-1',
  file: fs.createReadStream('audio.mp3'),
  language: 'en'
});

console.log(response.text);

<?php
$ch = curl_init('https://api.tokenlab.sh/v1/audio/transcriptions');

$file = new CURLFile('audio.mp3', 'audio/mpeg', 'audio.mp3');

curl_setopt_array($ch, [
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => [
        'Authorization: Bearer sk-your-api-key'
    ],
    CURLOPT_POSTFIELDS => [
        'file' => $file,
        'model' => 'whisper-1',
        'language' => 'en'
    ]
]);

$response = curl_exec($ch);
curl_close($ch);

$data = json_decode($response, true);
echo $data['text'];

{
  "text": "Hello, this is a test of the transcription API."
}

{
  "task": "transcribe",
  "language": "english",
  "duration": 5.5,
  "text": "Hello, this is a test of the transcription API.",
  "segments": [
    {
      "id": 0,
      "start": 0.0,
      "end": 2.5,
      "text": "Hello, this is a test",
      "tokens": [...]
    }
  ]
}

​
Terjemahan

Untuk menerjemahkan audio ke bahasa Inggris, gunakan endpoint translations: 
response = client.audio.translations.create(
    model="whisper-1",
    file=audio_file
)