Observed arrival · 2026-10-08
otoha: voice dialogue at the edge
otoha describes an on-device voice dialogue SDK and lightweight speech models for robots and other edge devices.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Robot and edge-device product teams
- Worth noticing
- The page reports p95 latency of 352.6 ms across 120 turns on a Ryzen 9 5900X, using rule-based dialogue.
Field notes
The described turn runs through voice activity detection, ASR, a replaceable dialogue “brain,” and TTS; the core is Rust exposed through a C ABI and distributed as binaries. The page says its piper-plus base runs on six runtimes and cites more than 70 speech models and 40 datasets on Hugging Face. Android and robot-hardware measurements remain future work.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
◎NicheUnusually specific use
One card from the complete issue