Hi everyone,
we have had trouble consistently getting realtime audio output in peninsular Spanish. The voice samples seem to be skewed towards south american Spanish, we have had some success by asking with almost every prompt to “speak in peninsular Spanish” but every ~10th word or so still comes out wrong.
Has anyone encountered and mastered this before?
Normalmente digo que escriba en castellano, pero lo del acento sudamericano nunca se va del todo con realtime. Si te cambias a los modelos que solo hacen “speech to text” o STT tendras mas suerte pero no pueden charlar agilmente como gpt-realtime. !Suerte!
Welcome to the dev community @mxzllr.
If I understand correctly, Peninsular Spanish is itself a group of distinct regional accents spoken in Spain’s Iberian Peninsula.
You can also prompt the model to speak as a person from a specific city, like Madrid for Castilian, Bilbao for Basque, or Seville for Andalusian accents, respectively.
Ah very interesting. I sort of thought that the sample size was muddled with different accents without being clearly marked, it never occured to me that it might be not specific enough.
Will give it a try - thanks!
