openai/gpt-4o-transcribe – Run with an API on Replicate

Official

openai / gpt-4o-transcribe

A speech-to-text model that uses GPT-4o to transcribe audio

Warm

Public
475 runs
Priced per token
Commercial use
License

Iterate in playground

Run with an API

Playground API Examples README

Input

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

audio_file

*file

The audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm

language

string

Shift + Return to add a new line

The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.

prompt

string

Shift + Return to add a new line

An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

temperature

number

(minimum: 0, maximum: 1)

Sampling temperature between 0 and 1

Default: 0

Run this model in Node.js with one line of code:

npx create-replicate --model=openai/gpt-4o-transcribe

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run openai/gpt-4o-transcribe using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  language: "en",
  audio_file: "https://replicate.delivery/xezq/XoxHeakty0z3KKc46cMLPKC2ct54ekT3EtvcwDQuRIuxfJdpA/tmpsglqtqn5.mp3",
  temperature: 0
};

for await (const event of replicate.stream("openai/gpt-4o-transcribe", { input })) {
  process.stdout.write(event.toString());
};

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run openai/gpt-4o-transcribe using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

# The openai/gpt-4o-transcribe model can stream output as it's running.
for event in replicate.stream(
    "openai/gpt-4o-transcribe",
    input={
        "language": "en",
        "audio_file": "https://replicate.delivery/xezq/XoxHeakty0z3KKc46cMLPKC2ct54ekT3EtvcwDQuRIuxfJdpA/tmpsglqtqn5.mp3",
        "temperature": 0
    },
):
    print(str(event), end="")

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run openai/gpt-4o-transcribe using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "input": {
      "language": "en",
      "audio_file": "https://replicate.delivery/xezq/XoxHeakty0z3KKc46cMLPKC2ct54ekT3EtvcwDQuRIuxfJdpA/tmpsglqtqn5.mp3",
      "temperature": 0
    }
  }' \
  https://api.replicate.com/v1/models/openai/gpt-4o-transcribe/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

So we just added GPT-4o transcribe to Replicate and thought you'd want to know. It's basically a speech-to-text model that uses GPT-4o to turn your audio into text. The cool thing is that it's noticeably better than the Whisper models we've been using, fewer errors, better at recognizing different languages, and just more accurate overall. If you've ever been frustrated with transcripts that mess up technical terms or struggle with different accents, you'll probably appreciate this upgrade. It just works better. Some quick tech specs if you're curious. It has a 16,000 token context window, which means it can handle longer audio clips in one go. And it can output up to 2,000 tokens, so you'll get nice complete transcripts. The model's knowledge is current up to June 2024, so it's pretty up-to-date with language and terminology.

{
  "completed_at": "2025-05-20T15:22:01.056014Z",
  "created_at": "2025-05-20T15:21:58.155000Z",
  "data_removed": false,
  "error": null,
  "id": "qj3j4z46hdrm80cpxs4ra9jsm8",
  "input": {
    "language": "en",
    "audio_file": "https://replicate.delivery/xezq/XoxHeakty0z3KKc46cMLPKC2ct54ekT3EtvcwDQuRIuxfJdpA/tmpsglqtqn5.mp3",
    "temperature": 0
  },
  "logs": "Input audio duration: 54.756 seconds\nInput token count: 912\nOutput token count: 174\nTotal token count: 1086\nTTFT: 1.38s",
  "metrics": {
    "input_token_count": 912,
    "tokens_per_second": 66.02314802304602,
    "output_token_count": 174,
    "predict_time": 2.894201353,
    "total_time": 2.901014,
    "time_to_first_token": 0.265574038
  },
  "output": [
    "So",
    " we",
    " just",
    " added",
    " GPT",
    "-",
    "4",
    "o",
    " trans",
    "cribe",
    " to",
    " Rep",
    "licate",
    " and",
    " thought",
    " you'd",
    " want",
    " to",
    " know",
    ".",
    " It's",
    " basically",
    " a",
    " speech",
    "-to",
    "-text",
    " model",
    " that",
    " uses",
    " GPT",
    "-",
    "4",
    "o",
    " to",
    " turn",
    " your",
    " audio",
    " into",
    " text",
    ".",
    " The",
    " cool",
    " thing",
    " is",
    " that",
    " it's",
    " noticeably",
    " better",
    " than",
    " the",
    " Whisper",
    " models",
    " we've",
    " been",
    " using",
    ",",
    " fewer",
    " errors",
    ",",
    " better",
    " at",
    " recognizing",
    " different",
    " languages",
    ",",
    " and",
    " just",
    " more",
    " accurate",
    " overall",
    ".",
    " If",
    " you've",
    " ever",
    " been",
    " frustrated",
    " with",
    " transcripts",
    " that",
    " mess",
    " up",
    " technical",
    " terms",
    " or",
    " struggle",
    " with",
    " different",
    " accents",
    ",",
    " you'll",
    " probably",
    " appreciate",
    " this",
    " upgrade",
    ".",
    " It",
    " just",
    " works",
    " better",
    ".",
    " Some",
    " quick",
    " tech",
    " specs",
    " if",
    " you're",
    " curious",
    ".",
    " It",
    " has",
    " a",
    " ",
    "16",
    ",",
    "000",
    " token",
    " context",
    " window",
    ",",
    " which",
    " means",
    " it",
    " can",
    " handle",
    " longer",
    " audio",
    " clips",
    " in",
    " one",
    " go",
    ".",
    " And",
    " it",
    " can",
    " output",
    " up",
    " to",
    " ",
    "2",
    ",",
    "000",
    " tokens",
    ",",
    " so",
    " you'll",
    " get",
    " nice",
    " complete",
    " transcripts",
    ".",
    " The",
    " model",
    "'s",
    " knowledge",
    " is",
    " current",
    " up",
    " to",
    " June",
    " ",
    "202",
    "4",
    ",",
    " so",
    " it's",
    " pretty",
    " up",
    "-to",
    "-date",
    " with",
    " language",
    " and",
    " terminology",
    "."
  ],
  "started_at": "2025-05-20T15:21:58.161812Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream-b.svc.ric1.c.replicate.net/v1/streams/aaxwjdhteahv5yvv7povzzkwb4cyzkw45jhqe4hvsususatqfhnq",
    "get": "https://api.replicate.com/v1/predictions/qj3j4z46hdrm80cpxs4ra9jsm8",
    "cancel": "https://api.replicate.com/v1/predictions/qj3j4z46hdrm80cpxs4ra9jsm8/cancel"
  },
  "version": "hidden"
}

Generated in

2.9 seconds

Input tokens

910

Output tokens

170

Tokens per second

66.02 tokens / second

Time to first token

0.3 seconds

Tweak it Report

Pricing

This model is priced by how many input tokens are sent and how many output tokens are generated.

Type	Per unit	Per $1
Input	$6.00 / 1M tokens or 160K tokens / $1
Output	$10.00 / 1M tokens or 100K tokens / $1

For example, for $10 you can run around 1,429 predictions where the input is a sentence or two (15 tokens) and the output is a few paragraphs (700 tokens).

Check out our docs for more information about how per-token pricing works on Replicate.

Readme

GPT-4o Transcribe is a speech-to-text model that uses GPT-4o to transcribe audio. It offers improvements to word error rate and better language recognition and accuracy compared to original Whisper models. Use it for more accurate transcripts.

16,000 context window
2,000 max output tokens
Jun 01, 2024 knowledge cutoff