Audio

Audio translation

Translate speech in any supported language into English text.

POST /v1/audio/translations

Transcribes an audio file and translates it into English in one step. The endpoint follows the OpenAI Audio API (audio.translations) and accepts multipart/form-data, so the official OpenAI SDKs work unchanged with base_url set to https://rutoken.ai/v1. The usual model is whisper-1.

To keep the original language, use Speech to text.

Authentication

Send your key in the Authorization: Bearer sk-xxxx header.

Request body

Content type: multipart/form-data. All form fields are forwarded to the upstream model.

Parameter	Type	Required	Description
`file`	file	Yes	Audio file: `flac`, `mp3`, `mp4`, `mpeg`, `mpga`, `m4a`, `ogg`, `wav` or `webm`. OpenAI limits uploads to 25 MB.
`model`	string	Yes	Model ID, e.g. `whisper-1`. If omitted, the request is routed as `whisper-1`.
`prompt`	string	No	Optional English text to guide the style of the translation.
`response_format`	string	No	`json` (default), `text`, `srt`, `verbose_json` or `vtt`.
`temperature`	number	No	Sampling temperature from `0` to `1`. Default `0`.

Request example

cURL

curl https://rutoken.ai/v1/audio/translations \
  -H "Authorization: Bearer $API_KEY" \
  -F file="@interview-de.mp3" \
  -F model="whisper-1"

Python

from openai import OpenAI

client = OpenAI(base_url="https://rutoken.ai/v1", api_key="sk-xxxx")
with open("interview-de.mp3", "rb") as audio:
    resp = client.audio.translations.create(model="whisper-1", file=audio)
print(resp.text)

Node.js

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://rutoken.ai/v1", apiKey: "sk-xxxx" });
const resp = await client.audio.translations.create({
  model: "whisper-1",
  file: fs.createReadStream("interview-de.mp3"),
});
console.log(resp.text);

Response

json

{
  "text": "Thank you for having me. Today I want to talk about renewable energy."
}

Field	Type	Description
`text`	string	English translation of the audio.

With response_format set to text, srt or vtt, the body is plain text instead of JSON.