GPT Realtime Translate is OpenAI's dedicated speech-to-speech translation model, released in May 2026 alongside GPT Realtime 2 as part of a refreshed realtime voice lineup. Trained on thousands of hours of professional interpreter audio, it detects the source language automatically across more than 70 spoken inputs and renders live translated speech in 13 target languages, with the target set by a BCP-47 code when the session starts. The model streams over a dedicated realtime endpoint, returning translated audio and transcript text while the speaker is still talking, and like a human interpreter it waits for enough context before committing to speech. It suits live interpretation in multilingual calls, meetings, broadcasts, classrooms, and any voice product where two languages need to flow in real time.
Usage-based pricing, billed by the minute, not by token.
| Variant | Price |
|---|---|
| Input | $0.034 / min |
GPT Realtime Translate runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Price |
|---|---|---|---|---|
| US | Enterprise | No | $0.034 / min |
GPT Realtime Translate runs on a single route through the Opper gateway today, so its availability is that provider's availability.
Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.
Each route hosting GPT Realtime Translate has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Call GPT Realtime Translate through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "openai/gpt-realtime-translate",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
