GPT-4o Transcribe is a speech-to-text model developed by OpenAI, built on the GPT-4o architecture. It delivers highly accurate audio transcriptions with significant improvements over previous models like Whisper. The model excels in diverse and challenging audio conditions, including accents, noisy environments, and varying speech speeds, making it ideal for robust and reliable transcription needs.
vs Whisper: GPT-4o Transcribe offers better transcription logic by understanding context, reducing errors and hallucinations that Whisper sometimes produces. Whisper remains reliable but lags behind in low-resource languages and challenging environments.
vs Google Speech-to-Text: Compared to Google Speech-to-Text, GPT-4o Transcribe provides a notably lower transcription error rate, making it more precise for complex audio inputs.
vs Deepgram: GPT-4o Transcribe leads with higher accuracy and better contextual awareness, reducing transcription errors and hallucinations, but Deepgram remains a strong competitor for real-time applications requiring optimized speed.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
import requests, time headers = {"Authorization": "Bearer " + AIMLAPI_KEY} job = requests.post( "https://api.aimlapi.com/v1/stt/create", headers=headers, json={ "model": "openai/gpt-4o-transcribe", "url": "https://example.com/audio.mp3" }, ).json() gid = job["generation_id"] while True: res = requests.get(f"https://api.aimlapi.com/v1/stt/{gid}", headers=headers).json() if res.get("status") in ("completed", "error", "failed"): break time.sleep(3) print(res)
const headers = { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }; const job = await (await fetch("https://api.aimlapi.com/v1/stt/create", { method: "POST", headers, body: JSON.stringify({ "model": "openai/gpt-4o-transcribe", "url": "https://example.com/audio.mp3" }), })).json(); let res; do { await new Promise((r) => setTimeout(r, 3000)); res = await (await fetch(`https://api.aimlapi.com/v1/stt/${job.generation_id}`, { headers })).json(); } while (!["completed", "error", "failed"].includes(res.status)); console.log(res);
# submit the job — the response contains "generation_id" curl -X POST https://api.aimlapi.com/v1/stt/create \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"openai/gpt-4o-transcribe","url":"https://example.com/audio.mp3"}' # then poll for the result until it is ready curl "https://api.aimlapi.com/v1/stt/{generation_id}" -H "Authorization: Bearer $AIMLAPI_KEY"
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Output | |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
GPT-4o Transcribe This page | Transcription | |||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis |
GPT-4o Transcribe takes audio as input and returns text.
GPT-4o Transcribe became available on December 30, 2025.
GPT-4o Transcribe is priced at $13 / 1M tokens.
GPT-4o Transcribe is billed per generation — a fixed charge per output rather than by prompt length.
GPT-4o Transcribe was built by OpenAI.
Send a request to v1 with openai/gpt-4o-transcribe as the model id.
Yes. GPT-4o Transcribe is served through AI/ML API, so the same key and endpoint format used for other models applies.
GPT-4o Transcribe has a 16,000 token context window and supports up to 2,000 max output tokens.
