21 karma · joined November 14, 2023
I am also experimenting with post-processing transcripts with LLMs to infer speaker names from a transcript. It works pretty decent already but it's still a bit expensive. I have this feature available under the 'enhanced' model if you want to check it out: https://docs.spectropic.ai/models/transcribe/enhanced
Thomas here, maker of Spectropic and Audiogest. I am indeed focused on building a simple and reliable Whisper + diarization API. Also working on providing fine-tuned versions of Whisper of non-English languages through the API.
Feel free to reach out to me if anyone is interested in this!
Currently I only have a discord channel for support and help, but your suggested approach of offering some included one on one consulting makes sense. I am gonna look into how I can implement this
However, the boilerplate also has a lot of other api routes, components and demo pages to setup an app.
If you're capable of easily setting that up yourself then this might not be for you, that's totally fine of course!