SpeechKit

SpeechKit is kombify’s local-first voice framework and runtime. The same public project provides a Go framework, a self-hosted server, agent tools, and a Windows reference client. The current public release is v0.52.14. SpeechKit is beta software: public APIs, configuration keys, and defaults can change between minor releases, so integrations should pin a version.

Three modes

Mode	Purpose
Dictation	Turn speech into text without LLM rewriting.
Assist	Turn speech or text into one useful result, optionally with spoken output.
Voice Agent	Run a realtime audio conversation for interactive work.

Hands-Free is an activation and output layer over these modes, not a fourth mode.

Choose a target

Windows client

Install the current Windows 10/11 x64 beta from the official release.

Go framework

Embed version-pinned voice capabilities into a Go application.

Understand the modes

Compare Dictation, Assist, Voice Agent, and their data boundaries.

Public repository

Browse source, examples, API contracts, and release notes.

Windows is the current desktop target. Linux is supported for the server runtime; macOS and Linux desktop packages are not currently available.

Get started

Framework and concepts

Three modes

Choose a target

Windows client

Go framework

Understand the modes

Public repository

​Three modes

​Choose a target

Windows client

Go framework

Understand the modes

Public repository

Three modes

Choose a target