hermes-ai.net

Read docs →
HermesHermes Agent Docs
News
Back to News
repoAudioOpen Source

Kizuna AI Lab's Sokuji Translates Live Calls Offline Without a GPU

Sokuji is an open-source live speech translator that runs entirely on-device with WASM and WebGPU, no API key or GPU required.

Kizuna AI Lab's Sokuji Translates Live Calls Offline Without a GPU
Source
AlphaSignal
Published
Author
AlphaSignal Newsroom
Read
1 min read

Sokuji is an open-source live speech translator that runs entirely on-device with WASM and WebGPU, no API key or GPU required.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Read original report

Next reads

Tencent's AuK Replaces 16 Speech Tools With One Open-Source Model
Tencent Hy · news

Tencent's AuK Replaces 16 Speech Tools With One Open-Source Model

YuE2-3B Beats Suno Generating Editable Full Songs on a Single GPU
AlphaSignal · model

YuE2-3B Beats Suno Generating Editable Full Songs on a Single GPU

audio.cpp Runs Speech and Music AI up to 5x Faster Without Python
AlphaSignal · repo

audio.cpp Runs Speech and Music AI up to 5x Faster Without Python