← Models

GPT-4o mini Transcribe

OpenAI · GPT-4o Audio

Lower-cost OpenAI speech-to-text tier for high-volume transcription pipelines.

Part of GPT family · Other versions: GPT-5.5 Pro , GPT-5.5 , GPT-Rosalind , GPT-5.4 mini , GPT-5.4 nano , GPT-5.4-Pro , GPT-5.4 , GPT-5.3 , GPT-5.3-Codex , GPT-5.2-Codex , GPT-5.2-Pro , GPT-5.2 , GPT-5-Codex , GPT-5 mini , GPT-5 , GPT-5 nano , GPT-4.1 , GPT-4o mini TTS , GPT-4o Transcribe , GPT-4o mini , GPT-4o
Type
audio
Context
16K tokens
Max Output
2K tokens
Status
current
API Access
Yes
License
proprietary
speech-to-text audio cost-efficient transcription api
Released March 2025 · Updated May 16, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on May 16, 2026.

GPT-4o mini Transcribe is OpenAI’s efficiency-focused STT tier for teams running high-volume audio-to-text workloads. OpenAI’s current model docs position it as the cheaper GPT-4o-based transcription route, with improved language recognition and accuracy compared with original Whisper models but lower quality than the full GPT-4o Transcribe tier.

Capabilities

The model handles common transcription and audio normalization tasks with practical quality for many operational use cases. It is well suited to routing pipelines where premium quality tiers are reserved for difficult clips and the majority of traffic needs cheaper transcription.

Technical Details

OpenAI’s current model card lists a 16K context window and 2K max output tokens. Those numbers are less important than file limits, language mix, and noise conditions, but they do help when you are building against tokenized transcript workflows in the API.

Pricing & Access

OpenAI’s current model docs list GPT-4o mini Transcribe audio-token pricing at 1.25per1Minputtokensand1.25 per 1M input tokens and 5.00 per 1M output tokens. It is exposed through OpenAI transcription endpoints and related API surfaces.

Best Use Cases

Strong fit for large-scale meeting ingestion, support call transcription, media indexing, and telemetry-heavy voice analytics pipelines.

Comparisons

Compared with GPT-4o Transcribe, mini roughly halves minute cost with quality tradeoffs on difficult audio. Compared with Whisper, it is the lower-cost modern OpenAI route. Routing hard clips upward remains a practical pattern.