Melvin Strobl 4df7bdb057 Speech calls keep one connection per server, opened when listening starts ...

transcribe and speak share an httpx client per speech server with a 300 s
keep-alive, and run on the engine's loop. stt warms it with GET /v1/models
when an utterance opens, so a reply's first sentence finds the connection
open: a new one over a lossy link cost up to a second (openpanel V4).

2026-10-19 22:06:08 +02:00

..

assets

Publish the documentation site: docs.fluksio.com

2026-08-22 05:55:34 +02:00

code

Voice nodes (openpanel V4): stt, tts, wren reply/unhandled, socket publish

2026-10-19 21:34:02 +02:00

concepts

Capability report: PUT /devices/{id}/report, a Capabilities section, offline devices degraded

2026-10-16 17:37:49 +02:00

getting-started

Panels become devices: per-device documents in the flow repo, a Devices tab

2026-10-16 15:48:36 +02:00

interface

Voice nodes (openpanel V4): stt, tts, wren reply/unhandled, socket publish

2026-10-19 21:34:02 +02:00

reference

Speech calls keep one connection per server, opened when listening starts

2026-10-19 22:06:08 +02:00

stylesheets

Publish the documentation site: docs.fluksio.com

2026-08-22 05:55:34 +02:00

index.md

Docs: x86 and arm64, Raspberry Pi included; one container in the start pages

2026-10-16 14:56:08 +02:00

llms.txt

A node's worker label is worker, so a device is only a paired one

2026-10-16 16:56:05 +02:00