RealtimeSTT

Speech to textOfflineGPU optionalCommercial use OK

Recording-based speech-to-text via RealtimeSTT (faster-whisper + VAD) for Record mode; also transcribes imported audio. GPU-accelerated when available.

Install it from Subtitld

Settings Add-ons RealtimeSTT Install

Subtitld downloads it, checks its SHA-256, and keeps it updated.

Source on GitHub

Languages: 30
Add-on download: 281–483 MB
RAM, at least: 2 GB

Options

In Settings › Add-ons › RealtimeSTT › Configure.

Model

Default: small

Device

Default: auto

Compute type

Default: default

Stream interim results

Default: on

Languages

en
pt
pt-br
es
fr
de
it
nl
ru
pl
uk
tr
ar
zh
ja
ko
hi
id
sv
fi
da
no
cs
el
he
ro
hu
ca
th
vi

Platforms

System	Download
Linux x86-64	482.7 MB
macOS (Apple silicon)	377.0 MB
Windows x86-64	280.6 MB

License

Add-on

MIT

MIT (wrapper + RealtimeSTT + faster-whisper); Whisper weights MIT

Versions

0.1.2

Other Speech to text add-ons

Updated 10 October 2026 · From the add-ons catalog Report a problem with this add-on