OpenAIGPT transcription

GPT-4o Mini Transcribe

GPT-4o Mini Transcribe is the smaller GPT-4o-based transcription release. The current catalog marks it deprecated; its listed snapshot is from December 2025.

Deprecated API; check access details

A smaller transcription release

The model accepts audio with text context and emits a transcript. It retains a 16,000-token context and a 2,000-token output ceiling. It is not a conversational audio model and does not generate a spoken answer.GPT-4o Mini Transcribe official model documentation

Review an existing integration

Practical guidance. For short voice messages, compare important-word accuracy and completion delay. Review names and amounts separately from ordinary sentences. Keep the transcription stage distinct from any later summarization or response generation.

Specifications & access

GPT-4o Mini Transcribe specifications
DetailValue and conditions
StatusDeprecated API; check access details
AccessAPI
Model identifiersgpt-4o-mini-transcribegpt-4o-mini-transcribe-2025-12-15
Context window16,000 tokens

Published context for this deprecated release

GPT-4o Mini Transcribe official model documentation
Maximum output2,000 tokens

Published maximum output, bounded by the remaining context

GPT-4o Mini Transcribe official model documentation
Provider statusDeprecated in the current OpenAI model catalog; confirm remaining account access.GPT-4o Mini Transcribe official model documentation

Related models

  • GPT-4o Transcribe

    OpenAI · GPT transcription

    GPT-4o Transcribe is a deprecated speech-recognition model based on GPT-4o.

    Launch date not confirmedDeprecated API; check access detailsAPI
  • GPT-Transcribe

    OpenAI · GPT transcription

    GPT-Transcribe turns recorded speech into text.

    Launch date not confirmedAPI
  • GPT-Live-Transcribe

    OpenAI · GPT transcription

    GPT-Live-Transcribe produces incremental text from live audio.

    Launch date not confirmedAPI
  • GPT-Realtime-Whisper

    OpenAI · GPT transcription

    GPT-Realtime-Whisper is a streaming transcription model for live speech.

    Launch date not confirmedAPI