Hello Guys,
I’m using OpenAI’s transcription API to transcribe audio files. However, I’ve noticed that it applies some automatic grammar corrections. For example, when I say “peoples” in the audio, the API transcribes it as “people.”
For my specific use case, I need the transcription to match exactly what is said in the audio, without any corrections or adjustments. Is there a way to disable this behavior and get a literal transcription?
If this feature doesn’t currently exist, where can I submit a suggestion for this functionality? It would be great if a parameter could be added to disable grammar corrections in future updates.
Thanks!