Skip to the card

Card 289 of 9812026-09-22 issue

Observed arrival · 2026-09-22

Fusion Runtime keeps the whole voice conversation on one GPU

fusion-runtime.dev Visit website
Editorial interest 84/100 Selection signal · not a rating of the site

A self-hosted voice-agent runtime that runs speech recognition, an LLM, and text-to-speech in one process on hardware you control.

Landing page captured for the 2026-09-22 issue.
For
Developers building private, low-latency voice interfaces
Worth noticing
The published benchmark separates roughly 490 ms of processing from a roughly 500 ms configurable silence wait.

Field notes

The documented pipeline combines Silero VAD, faster-whisper, llama.cpp, and Kokoro without a network hop between stages. The browser client handles echo cancellation and microphone resampling, while the backend mints a one-use token rather than exposing an API key in the page. Reported measurements use Qwen 7B, Whisper small, and Kokoro on an RTX 3090; long-call behavior remains unmeasured.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

OpenPublic substance visible
PrettyNotable craft visible
ProPolished or operationally mature
NicheUnusually specific use

One card from the complete issue

The Approximate Buildings of Mississauga

377,241 arrived 1,000 judged 981 catalogued Enter the complete issue
fusion-runtime.dev

Landing page observed 2026-09-22. The live site may have changed.