POST /v1/audio/transcriptions

Transcribe an audio file into text.

• Method: POST
• Path: /v1/audio/transcriptions
• Auth: Bearer token in Authorization header
• Content-Type: multipart/form-data

Request parameters

• model (string, required): Transcription model ID (e.g., gpt-4o-transcribe).
• file (binary, required): The audio file to transcribe.
• prompt (string, optional): Optional prompt to guide the transcription.
• language (string, optional): Language hint (BCP-47/ISO code if applicable).

Example requests

Python

from openai import OpenAI

client = OpenAI(base_url="https://api.naga.ac/v1", api_key="YOUR_API_KEY")

with open("audio.mp3", "rb") as f:
    transcription = client.audio.transcriptions.create(
        model="gpt-4o-transcribe",
        file=f,
        prompt=None,
        language=None,
    )
print(transcription.text)

Node.js

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({ baseURL: "https://api.naga.ac/v1", apiKey: "YOUR_API_KEY" });

const transcription = await client.audio.transcriptions.create({
  model: "gpt-4o-transcribe",
  file: fs.createReadStream("audio.mp3"),
  // prompt: "Transcribe clearly and include punctuation.",
  // language: "en",
});

console.log(transcription.text);

cURL

curl https://api.naga.ac/v1/audio/transcriptions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F file="@audio.mp3" \
  -F model="gpt-4o-transcribe"

Response

Returns a JSON object with the transcription result, e.g.:

{ "text": "Hello and welcome to NagaAI!" }