voice-ai

qvac: Build Private, Cross‑Platform AI Apps with On‑Device LLMs

Name: qvac: Build Private, Cross‑Platform AI Apps with On‑Device LLMs
Author: tetherto

qvac lets founders embed LLMs, speech‑to‑text, translation and more directly on Linux, macOS, Windows, Android and iOS, keeping data local and secure.

From the repo · “Open-source local AI SDK - run AI on-device with no cloud, no API keys. Supports GGUF, RAG, image, music, and video generation, speech-to-text, P2P inference, and more. Cross-platform: Linux, macOS, Windows, Android, iOS.”

705 stars+11★ this week140 forksTypeScriptGuide quality 9/10 · reviewed Oct 21Updated 10/22/2026100% free · open source

What it does

QVAC allows founders to run AI applications privately and locally on various platforms, including Linux, macOS, Windows, Android, and iOS, for building cross-platform AI tools.

When to use it

•When building AI-powered chatbots that require local data processing for security and privacy
•When developing speech-to-text or translation applications that need to run offline or on edge devices
•When creating peer-to-peer AI applications that require local model execution and data protection

Ready-to-paste prompt

Run a local speech-to-text model using QVAC with the command `npx tsc ts-example.ts && node ts-example.js --model speech-to-text`

Heads up: Ensure you have the necessary dependencies and toolchains installed, such as Node.js, npm, and the TypeScript compiler, and that your system meets the minimum requirements for running QVAC and its dependencies

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/qvac && curl -fsSL https://workflowstacks.com/api/skills/qvac/claude-skill -o ~/.claude/skills/qvac/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

top-level files

folders

321.6M

source size

Apache-2.0

license

Key files

.editorconfig

AGENTS.md

package.json

README.md

File tree

.agents/

.claude/

.cursor/

.github/

arch/

cmake/

docs/

packages/

plugins/

scripts/

vcpkg-overlays/

.editorconfig

.env.example

.gitattributes

.gitignore

AGENTS.md

CLAUDE.md

CONTRIBUTING.md

LICENSE

nx.json

package.json

pnpm-lock.yaml

pnpm-workspace.yaml

README.md

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/qvac && curl -fsSL https://workflowstacks.com/api/skills/qvac/claude-skill -o ~/.claude/skills/qvac/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

tetherto

Language

TypeScript

Related skills

More voice-ai tools founders pair with this one.

voice-ai★ 219,962

opencode: Code Faster

Get a coding agent with opencode, for founders. Backed by 191k+ GitHub stars.

voice-ai★ 78,422

Unsloth: Train AI Models

Train and run open AI models locally with Unsloth Studio, for founders. 68k+ GitHub stars

voice-ai★ 50,580

airi

💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing. Web / macOS / Windows supported.

voice-ai★ 28,349

cmux – Streamline AI‑Coding Workflows in macOS Terminal

A Swift‑powered terminal with vertical tabs and real‑time notifications, letting founders run multiple AI coding agents side‑by‑side. Ideal for macOS power users. 28k+ GitHub stars.

voice-ai★ 272

VideoHighlighter

Open-source local AI video analyzer powered by Ollama. Visual search, automatic highlights, scene/action/object detection, audio analysis, and subtitle generation. Free, offline alternative to Twelve Labs, Runway, and Descript.

voice-ai★ 9,623

inference: Swap Any LLM with a Single Code Change

Run open‑source, speech or multimodal models on cloud, on‑prem, or laptop through one production‑ready API—ideal for founders seeking flexible AI deployment. 9.6k+ GitHub stars