Loading
Live demos

whisper-1 shuts down on 26 February 2027

OpenAI retires whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe, gpt-4o-transcribe-diarize and the /v1/audio/translations endpoint on 26 February 2027. For files it recommends gpt-transcribe; for live audio, gpt-live-transcribe.

Checked on

whisper-1 OpenAI

Shutdown date: 26 February 2027

Official replacement: gpt-transcribe or gpt-live-transcribe

What changes in your code

  • For audio files OpenAI recommends gpt-transcribe; for audio that keeps arriving (a microphone, a call), realtime transcription.
  • With gpt-transcribe, languages (a list) replaces language: don’t send both. It also takes prompt and keywords for proper names.
  • If you used whisper-1 for subtitles, word timestamps or translation into English, gpt-transcribe isn’t the direct swap: the guide points to specialised models, and /v1/audio/translations becomes v1/realtime/translations.

Example code

Python
from openai import OpenAI
client = OpenAI()  # reads OPENAI_API_KEY from the environment

with open("audio.mp3", "rb") as f:
    t = client.audio.transcriptions.create(
        model="gpt-transcribe",     # was: "whisper-1"
        file=f,
        languages=["es"],  # was: language="es" (don’t send both)
    )
print(t.text)
Node.js
import fs from "fs";
import OpenAI from "openai";
const client = new OpenAI(); // reads OPENAI_API_KEY from the environment

const t = await client.audio.transcriptions.create({
  model: "gpt-transcribe",      // was: "whisper-1"
  file: fs.createReadStream("audio.mp3"),
  languages: ["es"],   // was: language: "es" (don’t send both)
});
console.log(t.text);

Sources: OpenAI · Deprecations · Speech to text

gpt-4o-transcribe OpenAI

Shutdown date: 26 February 2027

Official replacement: gpt-transcribe or gpt-live-transcribe

Sources: OpenAI · Deprecations

gpt-4o-mini-transcribe OpenAI

Shutdown date: 26 February 2027

Official replacement: gpt-transcribe or gpt-live-transcribe

Sources: OpenAI · Deprecations

gpt-4o-transcribe-diarize OpenAI

Shutdown date: 26 February 2027

Official replacement: gpt-transcribe or gpt-live-transcribe

Sources: OpenAI · Deprecations

Also on this page:

/v1/audio/translations OpenAI

Shutdown date: 26 February 2027

Official replacement: v1/realtime/translations

Sources: OpenAI · Deprecations

We’ll email you before your model is switched off

One email 30 days before and another 7 days before the official date, with the replacement and what changes in the code. Free, no account, no marketing.

Which models does your app use?
More models (39)

Using more than one model? Paste your code into the free checker.

Open the checker

Got a whole repository? Check it at once from the terminal, with nothing to install:

npx -y github:ericc2005t/ai-model-sunset

The code, on GitHub →

Questions

Does it work the same for subtitles (SRT, VTT)?
Not directly: OpenAI’s guide says gpt-transcribe is for transcription and points to specialised models if you need subtitles, word timestamps or translation.
What changes in the call?
The model and the language: languages (a list) replaces language, and you can’t send both.

Rather I fix it for you? Model swap, €79; full migration, €290–490. I reply within 24 h with a fixed price.

Ask for the fix: I reply within 24 h

No calls and nothing to pay here. Tell me what your app runs on and what breaks: I reply in writing within 24 h with a fixed price and a timeline.

What you need