★ 112,287 stars on GitHub · MIT license · Hand-picked by BANI
Free
Free accounts get 1 per month, Chick Members get 3 per month, Eagle Members get unlimited.
What it is
This is an open-source speech recognition model that turns speech into text in many languages, including Vietnamese, and runs on your own computer.
Who it is for
People who need to transcribe videos, meetings or lectures to make subtitles or write articles.
How to use it
Install Python and ffmpeg, then run the command-line tool on your audio file with the language set to Vietnamese. A faster community version is also available.
Good to know
Large models need a powerful computer; for Vietnamese, use the medium model or larger to get decent results.
This is an open-source tool by an outside author. BANI hand-picked it and wrote this overview; BANI does not own the tool.
After you claim it, the Download button opens the original page so you can install it. Tools only help you work faster; they do not guarantee views or income.
Star count checked on GitHub on Nov 9, 2026.