Closed OpenMachinesAI closed 1 week ago
There are no way of doing it using OpenAI's API, if you're talking about Text2Speech or Speech2Text, use the extensions that were already made for it.
Closing this as it's not a actual issue.
I’m referring to the real-time api not whisper
I’m referring to the real-time api not whisper
If it's not a problem, could you send the docs url for it?
https://platform.openai.com/docs/guides/audio
or if you wanna go down the webhook route: https://platform.openai.com/docs/guides/realtime
https://platform.openai.com/docs/guides/audio
or if you wanna go down the webhook route: https://platform.openai.com/docs/guides/realtime
Due to current pricing, we may not implement this feature. However, if OpenAI offers more competitive rates in the future, we might reconsider adding it.
I wanna make a voice interface in penguinmod. Please add other modalities like GPT-4o's voice and audio input/output and gemini's audio input