← Models

GPT-4o Transcribe

OpenAI · GPT-4o Audio

OpenAI speech-to-text model tier for production transcription and voice pipeline workflows.

Part of GPT family · Other versions: GPT-5.3-Codex , GPT-5.3 , GPT-5.4-Pro , GPT-5.4 , GPT-5.2-Codex , GPT-5.2-Pro , GPT-5.2 , GPT-5-Codex , GPT-5 nano , GPT-5 mini , GPT-5 , GPT-4.1 , GPT-4o mini Transcribe , GPT-4o mini TTS , GPT-4o mini , GPT-4o
Type
audio
Context
N/A
Max Output
N/A
Status
current
API Access
Yes
License
proprietary
speech-to-text transcription audio realtime api
Released March 2025 · Updated March 6, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on February 15, 2026.

GPT-4o Transcribe is OpenAI’s higher-quality speech-to-text model tier for converting spoken audio into text in product and operations workflows. It remains the quality-first OpenAI transcription route when teams want better accuracy than the lower-cost mini tier.

Capabilities

The model supports high-quality transcription for meeting capture, support workflows, and voice-enabled product features. It fits pipelines that need reliable text output from varied audio inputs, especially where speaker overlap, accents, or noisier clips matter.

Technical Details

For STT models, token contextWindow and maxOutput are not the right primary performance indicators. This profile sets both fields to 0 intentionally and treats them as N/A in token-oriented UI displays.

Pricing & Access

OpenAI’s current pricing docs list GPT-4o Transcribe at $6.00 per 1M audio input tokens. It is available through OpenAI’s audio model endpoints, with language support, file limits, and transport mode varying by endpoint and product surface.

Best Use Cases

Best for transcription services, searchable meeting notes, support call indexing, and ingestion pipelines feeding downstream summarization or QA systems.

Comparisons

Compared with GPT-4o mini Transcribe, this tier is positioned for higher quality. Compared with ElevenLabs speech workflows, selection depends on broader platform needs. Internal audio-set testing remains essential because vendor benchmarks rarely reflect your real noise and speaker mix.