Tag: speech-to-text

Showing 1-2 of 2

Sep 21, 20267 min readAgent PlaybookIntermediate

nanosamurai: an open-source, self-hosted speech AI platform — how to run a quick smoke test

A practical smoke-test for nanosamurai: an open-source, self-hosted speech AI. Clone the repo, use the docker-compose starter and confirm a 30‑second transcript locally.

nanosamurai speech-to-text ASR self-hosted docker-compose

+3 more

TutorialsUnited States

Open

Mar 26, 20267 min readModel Release BriefIntermediate90 min build

Prototype a low-latency live-audio demo with Gemini 3.1 Flash Live

Hands-on guide to prototype a minimal live-audio demo with Gemini 3.1 Flash Live. Build a mic→frames→model→captions loop, measure lag (<500 ms) and keyword recall for quick validation.

Gemini 3.1 audio AI live audio latency speech-to-text

+3 more

prototype tutorial Google