How I Built Transcriber - Local Whisper Voice Backend for Browser AI Tools

Voice input in the browser is a study in inconsistency.

Chrome, Edge, and most Chromium-based browsers have the Web Speech API with continuous recognition that works well for dictation. Firefox ships a stub that throws a not-supported error at runtime. Safari's implementation works but requires a permission gesture every few sentences. And all of them send your audio to a cloud service.

When I built voice dictation for PromptBoard, I needed something that worked everywhere and ran locally. Transcriber is the answer: a Node.js server that runs Whisper in-process and exposes a single HTTP endpoint. Any browser tool that wants voice input sends audio there and gets text back.

The cascade

Every Machina tool that supports voice uses the same three-level cascade:

Level 1 — Web Speech API (Chromium)

If window.SpeechRecognition is available, use it. Zero latency, zero network. Happy path for Chrome users.

Level 2 — Transcriber (port 4324)

For Firefox, MediaRecorder captures audio as a webm blob. On stop, it's POSTed to /transcribe. Transcriber converts to WAV with ffmpeg, runs Whisper, returns text. Round-trip: 1–3 seconds.

Level 3 — Manual fallback

If Transcriber isn't running and Web Speech isn't available, a dialog opens with the recorded audio and a textarea. Nothing is silently lost.

The API

GET  /health      → { ok, ready, model, language }

POST /transcribe  → { ok, text }  (body: raw audio bytes)

POST /shutdown    → graceful stop

Small surface, single responsibility. Transcriber doesn't manage sessions, doesn't store audio, doesn't know which tool is calling it.

The model downloads on first run (~150MB for whisper-base) and caches locally. You can swap models via env var:

TRANSCRIBER_MODEL=Xenova/whisper-small  # better accuracy, ~460MB

TRANSCRIBER_MODEL=Xenova/whisper-tiny   # faster, ~75MB

→ — a free, open-source suite of AI developer tools.