Gladia Live Transcription for OBS
Live captions overlay for OBS using the Gladia API.
Installation
Option 1: Install via script (easiest)
macOS / Linux
Open a Terminal and paste this command:
curl -fsSL https://raw.githubusercontent.com/KazeTachinuu/gladia-to-obs/master/install.sh | bash
Windows
Open PowerShell and paste this command:
irm https://raw.githubusercontent.com/KazeTachinuu/gladia-to-obs/master/install.ps1 | iex
Option 2: Manual download
- Go to the Releases page
- Download the file for your system:
- macOS:
transcription-mac-universal - Windows:
transcription-windows-x64.exe - Linux:
transcription-linux-x64
- macOS:
- macOS only: Remove the quarantine attribute (required for downloaded files):
xattr -cr ~/Downloads/transcription-mac-universal - Make it executable and run (macOS/Linux:
chmod +x <file>first)
Usage Guide
Step 1: Get a Gladia API Key (free)
- Go to gladia.io
- Create a free account
- Copy your API key from the dashboard
Step 2: Start the server
Open a Terminal (or PowerShell on Windows) and type:
transcription
A web page will open automatically in your browser.
Step 3: Configure transcription
On the web page that opened:
- Paste your API key in the “API Key” field
- Select your language from the dropdown
- Click “Start” to begin transcription
You should see text appearing in the “Preview” area.
Step 4: Add captions to OBS
- In OBS, click "+" in Sources
- Select “Browser” (or “Browser Source”)
- Give it a name (e.g., “Captions”)
- In the settings:
- URL:
http://localhost:8080/overlay - Width:
1920 - Height:
1080
- URL:
- Click OK
Captions will appear at the bottom of your screen with a transparent background.
To stop the server
In the Terminal, press CTRL + C.
Settings
Transcription
| Setting | Description |
|---|---|
| Language | Spoken language (or auto-detect) |
| Translate to | Optionally translate captions to another language |
| Custom Vocabulary | Names, brands, or technical terms to improve recognition |
Display
| Setting | Description |
|---|---|
| Position | Where captions appear on screen (X/Y) |
| Size | Font size (24–80px) |
| Style | Outline (Netflix-style) or background box |
Advanced
| Setting | Description |
|---|---|
| Response speed | How fast captions appear after speech (lower = faster) |
| Max segment | Maximum caption length before line break (5–20s) |
Development
# Development mode
bun run dev
# Build for current platform
bun run build
# Build for all platforms
bun run build:all
License
MIT
