Hi, has anyone started using speech to text model GPT-4o-transcribe using API yet? I understand this is conversation but I only want to use for speech to text. Any suggestions on alternative approaches and Any best practices tips? Thank you

Welcome to the community @saby Yes gpt-4o-transcribe can be used directly over the API for transcriptions and it comes with much higher quality transcriptions than whisper-1. It can be used for streaming transcriptions for both recorded audio and live-streaming audio .

Thank you @1uc4s_m4theus The real reason of wanting to this is the increased accuracy and real time streaming. Both are low on whisper model.

[image] sps: and it comes with much higher quality transcriptions than whisper-1. Is up to you to evaluate… [image] Gpt-4o-mini-transcribe and gpt-4o-transcribe not as good as whisper Feedback We recently migrated from Whisper to the new voice-to-text API but encou…

Did anyone noticed that gpt-4o-transcribe generates total nonsense? For example, if I use a code below with Whisper, it will generate a decent transcript. However, if I replace whisper with gpr-4o-transcribe (or mini) model, the output of the model will be totally random and not related to the audio…

having this exact issue. the audio is around the maximum length it allows (1500 seconds), I’m not sure if that’s related the problem but the response is totally random, often not even english.

Gpt-4o-mini-transcribe and gpt-4o-transcribe not as good as whisper frequently experiencing missed text. Due to these challenges, we reverted back to Whisper. Has anyone else experienced similar issues with the new API? Are you seeing Improvements in last 2 months @_j @farazs

gpt-4o-transcribe is the only transcription model selection still. There is no versioned/dated model to choose from, and no overwhelming anecdote of “we no longer have this problem”. For other endpoints: gpt-4o-realtime-preview-2025-06-03 gpt-4o-audio-preview-2025-06-03

@saby @_j @farazs If your not streaming, the problem has alway been the format of the transcription response - usually one big paragraph blob. Our solution is to run the transcription response through the “gpt-4.1” API: Developer Prompt: Identity You are language expert. You specialize in format…

OpenAI actually recommends gpt-4o-mini-transcribe over gpt-4o-transcribe now, so it’s worth giving that a shot to see if it works better for you. If you’re dealing with latency issues and missed text, you can also try a different transcription API that lets you switch between models (sometimes cert…

GPT-4o-transcribe and audio model ready to use via API?

API

saby July 2, 2025, 10:48am 9

Are you seeing Improvements in last 2 months @_j @farazs

Topic		Replies	Views
Gpt-4o-mini-transcribe and gpt-4o-transcribe not as good as whisper Feedback api	4	7835	January 10, 2026
Extracting Transcription Without Using input_audio.input_transcription in OpenAI API API realtime , api-realtime	10	738	March 11, 2025
GPT4.0-Transcribe—MAX 1500 SECONDS? API api	3	995	July 4, 2025
Introducing GPT-4o Transcribe Diarize: Now Available in the Audio API Community announcement , api , audio , transcribe , diarize	7	4420	November 14, 2025
Gpt-4o-transcribe truncates the transcript API transcribe	15	2815	August 29, 2025

GPT-4o-transcribe and audio model ready to use via API?

Related topics