The idea is:
OpenAI ChatGPT just came out with new audio transcription models per https://openai.com/index/introducing-our-next-generation-audio-models/. The built-in node for this, OpenAI Audio operations | n8n Docs, should allow the user to specify which of the available models to use to transcribe the recording.
My use case:
Transcribing voicemails with people’s names, that sometimes has low quality audio, into text. All the new models improve on these 2 features (names and low quality audio).
I think it would be beneficial to add this because:
It gives the user more control over the output.
Any resources to support this?
https://platform.openai.com/docs/api-reference/audio/createTranscription
Are you willing to work on this?
Sure, I am a software engineer but I haven’t worked on open source projects before.