GitHub Repository

An Electrobun app for generating audio clips from text using state of the art local LLMs

151 starsTypeScript

My 16MB vibe-coded voice cloning app

Name: My 16MB vibe-coded voice cloning app
Availability: InStock
Author: yoav

by yoav·Feb 17, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidDark HorseWizardryShip It

The Take

Shrinks the usual TTS bloat into a 16MB Electron-alternative wrapper while still letting you clone voices from a short sample and 'design' voices from text prompts. It handles model downloads for you, supports batch exports and macOS auto-updates — smart product trade-offs. Caveat: the app binary is tiny, but the underlying TTS models are downloaded on demand, so expect large model pulls behind the scenes.

Post Description

I vibe coded this text to speech app in an hour last weekend. It uses the new open weight Qwen models so it's fully local. Supports both instruct and voice cloning.

And since it's built with Electrobun it's only 16MB and uses typescript for the main and browser views.

Similar Projects

Gaming●●Solid

I vibe-coded a Hitster clone from my phone

Clone of Hitster built entirely via voice prompts to Claude from a car.

Ship ItBig Brain

38leinad

102mo ago

AI/ML●●Solid

Local Voice Assistant

This repo bundles a complete local audio loop — client captures audio, backend transcribes with Parakeet, queries a quantized Mistral LLM via Ollama, then renders speech with Kokoro or Qwen3-TTS for cloning — and reports ~1s round-trip on an RTX5070. It’s a practical, take-it-home demo for running privacy-first voice agents, though it’s still a demo: requires specific tooling (Ollama, GPU headroom), has obvious TODOs (VAD, better warmup for cloning), and isn’t reinventing the architecture.

WizardryNiche Gem

armcat

204mo ago

AI/ML●●Solid