language: en
audio_file: Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000

1x
Chapters
descriptions off, selected
captions settings, opens captions settings dialog
captions off, selected
Beginning of dialog window. Escape will cancel and close the window.
TextColorTransparency
BackgroundColorTransparency
WindowColorTransparency
Font Size
Text Edge Style
Font Family
End of dialog window.
temperature: 0

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

Install Replicate’s Node.js client library:

npm install replicate

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

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.

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 Share Report View full prediction

Prediction

openai/gpt-4o-transcribe

Official model

openai/gpt-4o-transcribe

eb25ct45wxrmc0cpxshtdf4jgw

Status

Succeeded

Source

Web

Total duration

4.8s

Created

27 days ago by @fofr

Input

language: en
audio_file
temperature: 0

{
  "language": "en",
  "audio_file": "https://replicate.delivery/pbxt/K5zuJ6HCdsffhegX0JZwDl10qm7fYAh5txe0FZc7XFccpdtm/kingnobelbig.mp4",
  "temperature": 0
}

Install Replicate’s Node.js client library:

npm install replicate

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/pbxt/K5zuJ6HCdsffhegX0JZwDl10qm7fYAh5txe0FZc7XFccpdtm/kingnobelbig.mp4",
  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

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/pbxt/K5zuJ6HCdsffhegX0JZwDl10qm7fYAh5txe0FZc7XFccpdtm/kingnobelbig.mp4",
        "temperature": 0
    },
):
    print(str(event), end="")

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

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/pbxt/K5zuJ6HCdsffhegX0JZwDl10qm7fYAh5txe0FZc7XFccpdtm/kingnobelbig.mp4",
      "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

I refuse to accept the idea that man is mere flotsam and jetsam in the river of life, unable to influence the unfolding events which surround him. I refuse to accept the view that mankind is so tragically bound to the starless midnight of racism and war that the bright daybreak of peace and brotherhood can never become a reality. I refuse to accept the cynical notion that nation after nation must spiral down a militaristic stairway into the hell of nuclear annihilation.

{
  "completed_at": "2025-05-20T15:50:26.710202Z",
  "created_at": "2025-05-20T15:50:21.927000Z",
  "data_removed": false,
  "error": null,
  "id": "eb25ct45wxrmc0cpxshtdf4jgw",
  "input": {
    "language": "en",
    "audio_file": "https://replicate.delivery/pbxt/K5zuJ6HCdsffhegX0JZwDl10qm7fYAh5txe0FZc7XFccpdtm/kingnobelbig.mp4",
    "temperature": 0
  },
  "logs": "Input audio duration: 49.157 seconds\nInput token count: 819\nOutput token count: 97\nTotal token count: 916\nTTFT: 3.95s",
  "metrics": {
    "input_token_count": 819,
    "tokens_per_second": 21.699802417079873,
    "output_token_count": 97,
    "predict_time": 4.778156903,
    "total_time": 4.783202,
    "time_to_first_token": 0.313115119
  },
  "output": [
    "I",
    " refuse",
    " to",
    " accept",
    " the",
    " idea",
    " that",
    " man",
    " is",
    " mere",
    " fl",
    "ots",
    "am",
    " and",
    " jets",
    "am",
    " in",
    " the",
    " river",
    " of",
    " life",
    ",",
    " unable",
    " to",
    " influence",
    " the",
    " unfolding",
    " events",
    " which",
    " surround",
    " him",
    ".",
    " I",
    " refuse",
    " to",
    " accept",
    " the",
    " view",
    " that",
    " mankind",
    " is",
    " so",
    " trag",
    "ically",
    " bound",
    " to",
    " the",
    " star",
    "less",
    " midnight",
    " of",
    " racism",
    " and",
    " war",
    " that",
    " the",
    " bright",
    " day",
    "break",
    " of",
    " peace",
    " and",
    " brother",
    "hood",
    " can",
    " never",
    " become",
    " a",
    " reality",
    ".",
    " I",
    " refuse",
    " to",
    " accept",
    " the",
    " cynical",
    " notion",
    " that",
    " nation",
    " after",
    " nation",
    " must",
    " spiral",
    " down",
    " a",
    " militar",
    "istic",
    " stair",
    "way",
    " into",
    " the",
    " hell",
    " of",
    " nuclear",
    " annih",
    "ilation",
    "."
  ],
  "started_at": "2025-05-20T15:50:21.932045Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream-b.svc.ric1.c.replicate.net/v1/streams/k4itpmb3jyrzag4wsbu6he3hujuvlru3jg5zweespvlikbaal4jq",
    "get": "https://api.replicate.com/v1/predictions/eb25ct45wxrmc0cpxshtdf4jgw",
    "cancel": "https://api.replicate.com/v1/predictions/eb25ct45wxrmc0cpxshtdf4jgw/cancel"
  },
  "version": "hidden"
}

Generated in

4.8 seconds

Input tokens

810

Output tokens

Tokens per second

21.70 tokens / second

Time to first token

0.3 seconds

Tweak it Share Report View full prediction