Observed arrival · 2026-10-17
Lana: a workbench for phonetic analysis
A free, open-source workbench for analyzing speech audio and building word, phone, and speaker tiers for TextGrid export.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Linguists annotating speech recordings
- Worth noticing
- A Dargwa sentence reportedly ran in under six seconds on a laptop processor, using MMS for words and ZIPA for phones.
Field notes
The browser demo runs Praat compiled to WebAssembly, but replays saved results from two readings in German and Georgian rather than transcribing a visitor's audio. The desktop preview is presented with hand annotation, microphone recording, TextGrid import from Praat or ELAN, and autosaving; the page says local models work offline after download. Its examples expose details such as an unassigned silence between speakers and a Dargwa run reported under six seconds on a laptop.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue