5 engineers on Hacker News describe using Whisper first-hand: 1 endorse it, 0 regret it, 0 are mixed.
“We run run Whisper Large V3 (not Turbo) for the speech to text. It still seems to be the best open source model out there for that step.”
endorse · production · WinH · 2024-12-16 · source ↗ · wrong label?“So we use yt-dlp to download the highest quality audio and then process them with whisper via Groq”
neutral · production · rob · 2025-06-25 · source ↗ · wrong label?“Storyteller uses Whisper to transcribe the audio to text (this is the most computationally expensive part of the process)”
neutral · production · smoores · 2023-12-25 · source ↗ · wrong label?“We also iterated heavily on the experience of recording yourself - e.g. tweaking our timeouts, moving from Twilio transcriptions to Whisper”
neutral · personal · eieio · 2023-12-23 · source ↗ · wrong label?“We use whisper in production and this is our findings”
neutral · production · atty · 2023-12-13 · source ↗ · wrong label?