Antix Realtime Speech — Transcription & Translation
Mic (camera), tab, URL, or file → live STT/Translate + subtitles
Credentials & Mode
Engine
Antix Speech Cloud 1
Whisper server
Speech Key
Region
eastus
eastus2
westus
westus2
centralindia
southeastasia
northeurope
westeurope
Mode
Transcription (STT only)
Translation (STT → multi-language)
Source
Microphone + Camera
Browser tab (Share audio)
Direct media URL
Local file (audio/video)
Select, then press
Start
. If autoplay is blocked, click play on the preview.
For YouTube/DRM: choose
Browser tab
and tick
Share audio
.
Idle
Output: Text + Subtitles
Start
Stop
Recognition Language (Speech STT locales)
Current:
English (United Kingdom) — en-GB
Target Languages (Antix Speech Cloud 1 Translator)
Add custom target code
Add
Preview, Subtitles & Sync
Subtitle renderer
Overlay (live)
Player CC (WebVTT)
Primary overlay language (live)
Overlay visibility
Auto (hide after ~2.5s)
Always show last line
Off
Overlay content
Both (partials + finalize)
Finals only
Partials only
Text direction
Auto (by language)
Left-to-right
Right-to-left
Text align
Start
Center
End
Video delay buffer (sec) — delay picture to match slower STT/translation
Apply Delay
Subtitle offset (sec) ± — shift cues vs video
Source (recognized)
Translations
Session Metrics
Session time
0:00
since start
Segments
0
finalized utterances
Words (src)
0
recognized
Avg. dur (s)
0.00
segment duration
Segments
Source
Translation
Lang
Duration (s)
Export Captions
Format
WebVTT (.vtt)
SubRip (.srt)
Language to export
Export
Clear collected segments
Tip: Export uses
final
segments only (no partials).
Events / Diagnostics
OK
NoMatch
Canceled
Clear