I m working on a small browser-based workflow for turning raw interviews and podcast episodes into a timestamped transcript, a short summary, show notes and subtitle drafts. The hard part does not seem to be generating text; it is keeping names, numbers, timestamps and speaker changes straight across a long recording.
For people who edit interviews or podcasts: what breaks first in your current workflow when the recording is 30 90 minutes? Names, numbers, timestamps, speaker changes, noisy audio, or turning the transcript into useful show notes?
If you have a public episode clip you are comfortable sharing, I m happy to turn one 30 60 second section into a transcript + SRT draft and report what still needs human review. No private upload needed.
I built Loqena because turning a one-hour interview into something usable still takes hours: transcribe it, find the quotes, write the summary, then prepare subtitles.
Loqena keeps that work in one browser workflow. Record or upload an interview, generate a timestamped transcript, turn it into key quotes, action items or show notes, and export TXT, SRT, VTT or JSON.
No meeting bot and no account is required to try the free minutes. Audio is processed only when you explicitly start transcription and is not written to object storage.
I would especially value feedback from podcasters, journalists and researchers who work with long interviews. The best test is your messiest real recording, not a clean demo clip.
If you want to inspect the output first, here is a real 19-second sample with the recording, transcript, quote and show-notes structure: https://loqena.com/en/guides/pod...