GPT Transcribe

GPT Transcribe

GPT-4o mini Transcribe is a speech-to-text model that uses GPT-4o mini 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.

Explore similar models

OpenAI

Whisper

General-purpose speech recognition model

$0.006 / minute

OpenAI

GPT‑5.2 Pro

The most capable model series yet for professional knowledge work.

$21.00/MTok

$168.00/MTok

400K

OpenAI

GPT-5.1

The best model for coding and agentic tasks across domains

$1.25/MTok

$10.00/MTok

400K

ElevenLabs

Scribe v2

ElevenLabs' state-of-the-art speech recognition model, delivering highly accurate transcription across 90+ languages with advanced features like speaker diarization, entity detection, and precise word-level timestamps.

$0.007/min

0

Google

Gemini 3.1 Pro

Google's frontier reasoning model delivering enhanced software engineering, agentic reliability, and multimodal intelligence across a 1M-token context window.

$2.00/MTok

$12.00/MTok

1.0M

ByteDance

Seedance 2.5 Turbo

ByteDance's high-performance Seedance 2.5 Turbo suite for cinematic video generation from text, image, or existing video, offering faster and more affordable outputs at 720p and 1080p.

$1.00-$12.00/video

50K

OpenAI

GPT-4o TranscribeDeprecated

Speech-to-text model powered by GPT-4o