mrtozner

mrtozner / vox

Public

Local voice AI framework for Rust. Whisper + LLM + TTS with no cloud dependencies.

local-ai ollama rust speech-to-text stt
16
3
100% credibility
Found Feb 17, 2026 at 11 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Rust
AI Summary

Vox is a local voice AI toolkit that handles speech-to-text transcription, text-to-speech synthesis, and interactive voice chat entirely on your computer without cloud services.

How It Works

1
🔍 Discover Vox

You hear about Vox, a simple tool that lets your computer listen to your voice, understand it, and even talk back—all happening right on your machine for total privacy.

2
📥 Set it up

With one easy command, you download Vox and get ready to use it—no complicated steps or accounts needed.

3
🎵 Add voices

Vox grabs natural-sounding voices automatically the first time, so everything sounds real and smooth.

4
🎙️ Speak and see magic

Talk into your microphone, and watch your words turn into text on screen in real time—it's instant and accurate.

5
🗣️ Hear it reply

Type or say a message, pick a friendly voice, and Vox speaks it back clearly through your speakers.

6
💬 Chat naturally

Start a back-and-forth conversation where Vox listens, thinks with a local helper brain, and responds out loud.

7
🌐 Web playground

Open a browser page to test listening, speaking, and chatting with buttons and live results.

✅ Private voice world

Now you have your own voice assistant that works offline, keeps everything secret, and feels like magic every day.

Sign up to see the full architecture

6 more

Sign Up Free

Star Growth

See how this repo grew from 11 to 16 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is vox?

Vox is a Rust framework for building local voice AI pipelines, chaining microphone input through voice detection, speech-to-text via Whisper or Sherpa, optional LLM integration, and text-to-speech with engines like Kokoro or Piper—all without cloud dependencies. Developers get instant CLI tools like `vox listen` for transcription, `vox speak` for synthesis, `vox chat` for voice conversations with local LLMs like Llama via Ollama, plus a web server for HTTP/WebSocket APIs and Python bindings. It's github vox populi for local voice ai, solving privacy leaks in cloud voice assistants by keeping everything on-device.

Why is it gaining traction?

In a world of leaky APIs, Vox stands out with zero-config local voice chat, real-time streaming transcription over WebSocket, and pluggable backends for multilingual STT/TTS including voice cloning. The `vox serve` command spins up a browser UI for testing, while HTTP endpoints like `/v1/transcribe` and `/v1/synthesize` make it a drop-in local voice llm or copilot alternative—no API keys needed. Early adopters love the Ollama integration for local voice assistant setups rivaling github copilot but offline.

Who should use this?

Rust embedded devs crafting local voice assistant hardware, Home Assistant tinkerers adding mic input to smart homes, or AI prototype hackers needing a local voice changer/cloning ai without vendor lock-in. Ideal for local github actions runners processing voice commands offline or building private voice chat apps.

Verdict

Grab Vox if you need a lightweight local voice ai foundation—CLI and API are polished, docs solid with benches, but at 11 stars and 1.0% credibility, it's early-stage; test thoroughly before production. Promising for offline prototypes.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.