NOEMIUMobservatory

01 /TOOLS / whisper

Whisper

shipSteady momentum

OpenAI's open-weights speech recognition — the default transcription model.

github.com

journal entry · observed by @whysanesanders · verified 2026-08-15

The reason paid transcription became a niche: large-v3 accuracy is production-grade across dozens of languages and it runs on a laptop. Every transcription pipeline starts here.

Known limitations

  • Hallucinates text on silence and noisy segments.
  • No built-in speaker diarization (pair with pyannote).
  • large-v3 needs a decent GPU for real-time work.

Facts

pricing
free
price note
free (open weights); hosted API $0.006/min
free tier
yes
open source
yes
api
yes
self-host
yes
category
audio

Models used

whisper-v3

Receipts

Edit this page on GitHub

Same sector — audio