GPT-4o Mini Transcribe is a speech-to-text model from OpenAI designed to deliver highly accurate and efficient audio transcription. It represents a lighter, faster version of the full GPT-4o-Transcribe model, optimized for lower latency and resource consumption while maintaining excellent transcription quality. This model is ideal for developers seeking quick, reliable speech recognition in diverse and challenging acoustic environments.
vs GPT-4o Transcribe: Mini Transcribe is better for low-latency applications, whereas the full Transcribe model suits accuracy-critical environments like legal or medical transcription.
vs OpenAI Whisper-Large: GPT-4o Mini Transcribe outperforms Whisper-Large in word error rate (WER) and streaming latency, thanks to reinforcement learning and specialized audio training. Whisper is more general-purpose but tends to be slower and less precise on noisy or accented speech.
vs Eleven Labs Scribe: While both models excel in streaming transcription, Eleven Labs Scribe reportedly matches or slightly exceeds GPT-4o-Mini-Transcribe in accuracy benchmarks in some third-party tests. GPT-4o-Mini speeds and integration with OpenAI’s ecosystem remain strong advantages.
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-mini-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 ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }; const job = await (await fetch("https://api.aimlapi.com/v1/stt/create", { method: "POST", headers, body: JSON.stringify({ "model": "openai/gpt-4o-mini-transcribe", "url": "https://example.com/audio.mp3" }), })).json(); let res; do { await new Promise((r) => setTimeout(r, 3000)); res = await (await fetch(`https://api.aimlapi.com/v1/stt/${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-mini-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 Mini Transcribe This page | Transcription | |||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis |
GPT-4o Mini Transcribe takes audio as input and returns text.
GPT-4o Mini Transcribe became available on December 30, 2025.
GPT-4o Mini Transcribe is priced at $6.5 / 1M tokens.
GPT-4o Mini Transcribe is billed per generation — a fixed charge per output rather than by prompt length.
GPT-4o Mini Transcribe was built by OpenAI.
Send a request to v1 with openai/gpt-4o-mini-transcribe as the model id.
Yes. GPT-4o Mini Transcribe is served through AI/ML API, so the same key and endpoint format used for other models applies.
Yes, OpenAI describes it as having improved accuracy compared to Whisper.
It has a 16,000 token context window and a maximum output of 2,000 tokens.
