Transcribe

Ubah audio menjadi teks lewat endpoint kompatibel OpenAI. Tiga model: gpt-4o-transcribe (paling akurat), gpt-4o-mini-transcribe (lebih murah), dan whisper (ditagih per menit).

POST https://api.nexotao.com/v1/audio/transcriptions   (multipart/form-data)

Contoh

curl https://api.nexotao.com/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-nexo-..." \
  -F file=@rapat.mp3 \
  -F model=gpt-4o-transcribe \
  -F language=id

from openai import OpenAI
 
client = OpenAI(base_url="https://api.nexotao.com/v1", api_key="sk-nexo-...")
 
with open("rapat.mp3", "rb") as f:
    t = client.audio.transcriptions.create(
        model="gpt-4o-transcribe",
        file=f,
        language="id",
    )
print(t.text)

import OpenAI from "openai"
import fs from "fs"
 
const client = new OpenAI({ baseURL: "https://api.nexotao.com/v1", apiKey: "sk-nexo-..." })
 
const t = await client.audio.transcriptions.create({
  model: "gpt-4o-transcribe",
  file: fs.createReadStream("rapat.mp3"),
  language: "id",
})
console.log(t.text)

Parameter & batas file

Parameter	Wajib	Keterangan
`file`	ya	berkas audio (mp3, wav, m4a, webm, mp4, mpeg, mpga, ogg, flac)
`model`	ya	`gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, atau `whisper`
`language`	tidak	kode ISO, mis. `id` untuk Indonesia — mempercepat & mempertajam hasil

Ukuran maksimum berkas: 25 MB.

Penagihan

gpt-4o-transcribe / mini: per token audio + token teks keluaran.
whisper: per menit durasi audio.

Tarif persis ada di Model & Harga. Saldo dipotong setelah transkrip selesai.

Generate Gambar Claude Code