What is the difference between realtime-transcription and speech-to-text for Streaming the transcription of an ongoing audio recording?

API
, , , ,
1

I’m trying to transcribe audio to text in real-time with microphone audio streamed over websocket to openai via javascript SDK … I want to know the difference between https://platform.openai.com/docs/guides/realtime-transcription and https://platform.openai.com/docs/guides/speech-to-text for Streaming the transcription of an ongoing audio recording

1 Like
2

speech-to-text enables streaming of the output, but takes a complete audio file as input

realtime can take streams as input and ouput

1 Like
3

My bad need to pay attention to details… the “ongoing recording” is using the same realtime transcription endpoint so its’ the same :slight_smile: