OpenAI Speech to Text API review

OpenAI's speech-to-text sits inside the same API most AI developers already use. For recorded audio, gpt-transcribe costs $0.0045 per minute and accepts keyword lists, language hints and a free-text prompt describing the recording, which helps with product names and account codes. For live audio from a microphone or phone call, gpt-live-transcribe streams text as the speaker talks for $0.017 per minute. Diarization runs through gpt-4o-transcribe-diarize, which can match known speaker names, but OpenAI notes speaker labels are not supported in realtime sessions. The older gpt-4o-mini-transcribe remains available at $0.003 per minute, and the original whisper-1 model is deprecated, so new projects should start on gpt-transcribe. Uploads are capped at 25 MB, which means long recordings must be compressed or split. OpenAI does not publish a latency figure for live transcription. The setup is simple if you already have keys and billing in place.

Who it is for

Teams already on the OpenAI API who want transcription without adding a vendor.

Price

Usage only: gpt-transcribe $0.0045 per minute for batch, gpt-live-transcribe $0.017 per minute for live audio; older gpt-4o-mini-transcribe $0.003 per minute.

A speech-to-text model for asynchronous and batch workloads. Price $0.0045 per minute
Quoted from the vendor pricing page on November 7, 2026.

Key features

• gpt-transcribe for file and batch transcription with keyword and language hints
• gpt-live-transcribe streams text as the speaker talks
• Speaker labels with gpt-4o-transcribe-diarize and known speaker names
• Prompts for unstructured context about the recording
• Same API keys, SDKs and billing as other OpenAI models

Strengths and weaknesses

• Strength: Nothing new to sign up for if you already use OpenAI
• Strength: Batch rate of $0.0045 per minute is competitive
• Strength: Keywords and prompts help with names and jargon
• Weakness: Live transcription at $0.017 per minute is the highest published streaming rate here
• Weakness: Files are limited to 25 MB per request
• Weakness: Speaker labels are not supported in realtime sessions

Key facts

• File limit: 25 MB per upload
• Diarization: Files only, via gpt-4o-transcribe-diarize
• Legacy model: whisper-1 is deprecated

Where it ranks

OpenAI Speech to Text API is No. 6 in our Best Speech-to-Text APIs verdict.