BREAKING
Sokuji: Real-Time Voice Translation
Cloud vs Local Inference
Cloud mode
Accuracy
●
OpenAI, Gemini, Palabra.ai
●
Needs API key + internet
Local mode
Privacy
●
WASM + WebGPU on device
●
No API key, works offline
On-Device Pipeline
1
Speech recognition
↓
2
Translation
↓
3
Speech synthesis
Plugs Into Meet, Teams, Zoom
Open Source Sets It Apart
Rivals
●
KUDO, Soniox, LiveVoice
●
Cloud-focused, closed
Sokuji
Open
●
Fully offline option
●
Published by Kizuna AI Lab
Balancing Cost and Privacy
AI NEWS BLITZ
An open-source app translates speech in real time, in the cloud or right on your device.