Hi everyone, I’ve spent a lot of time trying to build a reliable speech-to-text pipeline using OpenAI’s transcription models—both through the /v1/audio/transcriptions endpoint and the new real-time /v1/realtime WebSocket API (using the gpt-4o-transcribe model). I’ve tested this through a custom bro…

Persistent Truncation Issues with GPT-4o-Transcribe – Has Anyone Fully Solved This?

jeffvpace July 5, 2025, 7:48pm 12

Your use case is probably one of the most important and widely used cases for STT.

1 Like

Gpt-4o-transcribe truncates the transcript

Topic		Replies	Views
Gpt-4o-transcribe truncates the transcript API transcribe	15	2670	August 29, 2025
Prompt Fatigue Question For API Calls Prompting gpt-35-turbo	24	893	January 25, 2025
[Realtime API] Audio is randomly cutting off at the end Bugs realtime , api-realtime	86	7412	February 2, 2026
New 4-turbo model has a unique limit? Or is this a bizarre hallucation? API	18	4661	January 26, 2024
Gpt-4o-transcribe truncates output after ~8-9 minutes even on short segments Bugs transcribe	3	361	August 29, 2025