POST /v1/audio/translations

Translate an audio file into English.

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

Request parameters

• model (string, required): Translation model ID (e.g., whisper-large-v3).
• file (binary, required): The audio file to translate.
• prompt (string, optional): Optional prompt to guide the translation.
• language (string, optional): Source language hint (if known).

Example requests

Python

from openai import OpenAI

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

with open("german.mp3", "rb") as f:
    translation = client.audio.translations.create(
        model="whisper-large-v3",
        file=f,
        # prompt="Translate clearly with punctuation."
    )
print(translation.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 translation = await client.audio.translations.create({
  model: "whisper-large-v3",
  file: fs.createReadStream("german.mp3"),
  // prompt: "Translate clearly with punctuation."
});

console.log(translation.text);

cURL

curl https://api.naga.ac/v1/audio/translations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F file="@german.mp3" \
  -F model="whisper-large-v3"

Response

Returns a JSON object with the translated text, e.g.:

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