Observed arrival · 2026-09-21
Voxint — Local Speaker-Labeled Transcripts
An open-source tool that turns recordings into speaker-labelled transcripts on your own hardware.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Researchers, journalists, educators, and small teams
- Worth noticing
- Speaker proposals remain separate from user rulings, creating a review queue and provenance trail.
Field notes
Voxint separates the automated transcript and speaker proposals from the operator’s corrections, making review part of the workflow rather than an afterthought. Its installation path uses Docker Compose and a provided shell script, while the site says processing can run on CPU with roughly 8 GB of free memory. The project identifies Whisper, pyannote, and TitaNet as its local processing components and offers several text, subtitle, and structured-data exports.
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