This page walks through installation, FFmpeg and Ollama setup, model download, and the first successful test. Tutorial videos are a highlighted use case, but the app is not limited to them.
You do not need a lot, but a few base components must be in place. Once they are ready, the setup assistant can check the whole chain quickly.
Start on the download page. The portable ZIP package should be extracted into a separate folder, and VoxBridge Studio should be started from that extracted folder.
You can run the commands below in PowerShell or cmd.
Where there is a difference, it is written explicitly.
FFmpeg is required for video and audio processing. If the app cannot find it automatically, you can point the app to it manually.
The featured download button above goes to the official page.
C:\Tools\ffmpeg.bin folder to PATH, or keep the full path handy.ffmpeg -version.ffmpeg.exe.ffmpeg -versionIf this prints a version number, FFmpeg is visible to the system.
If it is not found, either it is not installed or it is not in PATH. Manual path entry inside the app is the quickest fallback.
# 1) Create the folder
New-Item -ItemType Directory -Force -Path C:\Tools\ffmpeg
# 2) Extract the FFmpeg package here
# Skip this if you already extracted it
# 3) Check whether ffmpeg.exe exists
Get-ChildItem C:\Tools\ffmpeg -Recurse -Filter ffmpeg.exe
# 4) Add the bin folder to the current session PATH
$env:Path += ";C:\Tools\ffmpeg\bin"
# 5) Verify it
ffmpeg -version
where.exe ffmpegmkdir C:\Tools\ffmpeg
where ffmpeg
set PATH=%PATH%;C:\Tools\ffmpeg\bin
ffmpeg -version
If ffmpeg -version works only in the current terminal, the PATH change is temporary.
In that case either set PATH permanently in Windows, or point the app directly to ffmpeg.exe.
Ollama runs the local model. For the first setup, a working local Ollama instance is enough as long as the app can reach it.
The featured download button above goes to the official Windows page.
ollama --version.ollama list.ollama --version
ollama listThe setup assistant can check this too, but it helps to verify it manually first.
# 1) Check the version
ollama --version
# 2) See whether it responds
ollama list
# 3) Start the local service manually if needed
ollama serveollama --version
ollama list
ollama serve
ollama serve is usually only needed if Ollama is not already running.
If ollama list works right after install, you often do not need to start it separately.
The default path is based on a local translation model that is easy to understand and run. If the app suggests a different model later, follow that recommendation.
ollama list.ollama pull translategemma:12b
ollama pull translategemma:27b
translategemma:12b is the easier and faster starting point.
translategemma:27b usually gives better translation quality, but it can be
slower and needs a stronger machine with more memory. Start with 12b for the first
working setup, then try 27b if translation quality matters more and the machine can handle it.
# Easier starting model
ollama pull translategemma:12b
# Larger, usually better-quality model
ollama pull translategemma:27b
# Verify
ollama listollama run translategemma:12b "Translate to Hungarian: Hello, this is a short test."
ollama run translategemma:27b "Translate to Hungarian: Hello, this is a short test."
If ollama run returns a sensible translation, the model is really running.
The 27b model is listed separately because it usually gives better translation quality.
| Minimum | Recommended |
|---|---|
|
Windows 10 or newer FFmpeg installed running Ollama 16 GB RAM SSD storage |
Windows 11 32 GB RAM or more fast SSD stronger CPU or GPU stable internet for the initial model download |
The goal here is not perfection. The goal is the first green status.
Start with a short, non-private video, not with an important long course recording. A sidecar subtitle is the easiest first case.
VideoName.hu.srt.
If it still does not start, create a support export and send it to support. It can include logs, settings and technical state information.