AI Agents

Topshe: voice AI that runs entirely in your browser

2026-08-22 · 7 min read

The short answer

Topshe is a voice assistant that never calls home. Wake word to speech-to-text to a quantised Qwen 2.5 LLM execute inside the browser over WebAssembly — no server, no API key, no data leaving the phone. The experiment that cost zero/month taught me where edge AI wins and where it still loses.

Most people assume a voice AI assistant must phone a cloud. For Topshe (Bengali for "sits" — the quiet one), the entire stack runs locally: React 19 shell, Web Speech for input, a quantised Qwen 2.5 model inferring through WASM, offline-capable as a PWA.

Why edge

  • Privacy without a story. Nothing leaves the device — no transcripts recorded by a vendor
  • $0/month with real inference, not an API token funnel
  • PWA — works as an app, no install, offline capable

The honest tradeoffs

  • Model size vs quality. Quantisation shaves latency but taxes clever summarisation; the assistant is snappier than deep, by design.
  • Memory ceiling. Not every mobile device runs a 7B model comfortably in-browser; we size the model to the device.
  • Wake-word dev. WASM audio wakes fast, but speaker environments still puzzle it.

What it demonstrated

Edge LLMs are production-viable for small systems with clear intents — a light assistant, a noise tool, a vault-adjacent copilot. They are not (yet) full cloud-grade chat without a compute fallback.

The recruiter-agent post and Topshe bookend the same taste: I keep reaching for the smallest system that gives the product to the user. Topshe is the smallest.

What I'd do differently

  • Ship wake-word tuning before claiming "hands-free" — the demo works, the hallway doesn't.
  • Benchmark on a mid-tier phone. We demoed on silicon that flattered the WASM numbers.

The projects page holds the live demo link and the open-source repo.

Frequently asked questions

Can a large language model run on a browser?+
Yes for small quantised models. Topshe runs Qwen 2.5 quantised through WebAssembly on a phone; bigger models need a machine.
Why run AI in the browser instead of an API?+
Privacy and $0 marginal cost — no prompt leaves the device, no vendor API bill on a quiet day.
Is browser voice AI practical for daily use?+
Today: yes for dictating and light tasks. Browser WebAssembly ticks under a second on modern devices; heavy reasoning still offloads.
S

Saswata S. Sengupta

PM at Upcore Technologies. Cut checkout abandonment 73.1% to 53.9%. IIT Jodhpur MBA. All posts are grounded in shipped work with published numbers.

Keep reading