We’re starting to scale our automation builds and transcribing client videos has become the main bottleneck for our current setup.
Many clients share with us their course content (often via Dropbox or Google drive) so we can ingest and build their content agents.
Up until this point we have been doing a lot of semi-manual work like using Descript to transcribe their videos but this is both more expensive than I’d like and too hands-on to properly scale.
So I’m wondering what are others using to transcribe video files?
Is google’s Speech transcription good enough? Maybe OpenAI?
Something else?