Text Embedding 3 Small turns text of up to about 8 pages into a fingerprint of its meaning, so search finds passages that mean the same thing even when the words differ. It replaces the older ada-002 and is the sensible default for search over your documents, grouping similar messages or labelling them.
GPT-4o Transcribe
by OpenAIReleased 27 April 2026
OpenAI's high-quality transcription model, built on the audio skills of GPT-4o for speech-to-text where accuracy leads; GPT-4o Mini Transcribe is the smaller, high-volume model of the pair
Billed by the token
Questions about GPT-4o Transcribe
Is GPT-4o Transcribe still on sale?
No. OpenAI has retired it. Other OpenAI models are on sale.
What is GPT-4o Transcribe best for?
OpenAI's high-quality transcription model, built on the audio skills of GPT-4o for speech-to-text where accuracy leads; GPT-4o Mini Transcribe is the smaller, high-volume model of the pair.
Does GPT-4o Transcribe work in Arabic, French or Darja?
OpenAI names no languages for GPT-4o Transcribe. Arabic, French and Darja: not stated.
Does it say who spoke, and when?
Speaker labels: not stated. Word timings: not stated.
How long can a file be?
Up to 25 MB as an upload. Longer audio goes in the request body.
Who makes GPT-4o Transcribe, and when was it released?
OpenAI. Released 27 April 2026. It knows the world up to June 2024.
Other OpenAI models, priced in dinars
See all OpenAI modelsGPT Image 2.5 Sunburst takes a written description, with optional reference pictures, and gives back an image, new or edited, as PNG, JPEG or WebP, with transparent backgrounds on PNG and WebP. It is the precision tier of the 2.5 series, for detailed creative work where an edit has to land exactly as asked, and it adds top quality settings named xhigh and max.
GPT-6 Luna Decisions does not write text. You send content as text, a table of data or a picture, plus up to 200 named questions of three kinds: yes or no, pick among options, or grade against an ordered scale. It returns a probability for every answer, with the likeliest option or expected score, so your own system can set its thresholds for routing, moderation or marking.
Text Embedding 3 Large turns text of up to about 8 pages into a fingerprint of its meaning, so search finds passages that mean the same thing even when the words differ. It is the most accurate of OpenAI's models of this kind, in English and other languages. Choose it when the quality of matches matters most, for search, grouping or labelling documents.