Does anyone know when OpenAI’s text-to-speech models (like gpt-4o-mini-tts) will be implemented in the n8n OpenAI Generate Audio node? I’ve checked, and this model provides much better voices for generating audio (such as ‘Ash’, ‘Ballad’, ‘Coral’, ‘Sage’, ‘Verse’). It would be great to have this feature. Or does anyone know if it’s possible to add it on my own?
I used TTS services by sending an HTTP Requests till now and not for OpenAI specifically. But I suppose that every service must have an endpoint if it’s OpenAI we are talking about. Make sure to check their documentation they have detailed information about every endpoint they offer and its required parameters.
yes, you are absolutly right. Thanks! I’ll check maybe I can implement it or will use HTTP Request.
This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.