v0.2 · macOS · Two ways to dictate

Voice dictation for macOS, your way.

Hold a hotkey. Talk. Release. The transcript is polished into structured text and pasted at your cursor in any app. Run it offline on your Mac for free, or use our hosted service for zero local memory and faster latency.

Hold Option · the floating pill shows your voice in real time

Susurro Local

Free, forever

$0 · MIT licensed

Runs entirely on your Mac. No accounts, no subscriptions, no data leaves your machine.

  • Whisper STT on-device via Apple's MLX
  • Llama 3.2 3B polish on-device (smart formatting, lists, fillers)
  • Works fully offline — no internet required after install
  • Open source, MIT, audit any line
  • Uses ~3 GB RAM while running
  • Apple Silicon (M1+) required
Install free →
Susurro Pro

For everyday dictation

$10 /month

Cloud transcription with our keys. Zero local memory. WisprFlow-tier latency. Free tier: 2,000 words/month.

  • 100,000 words/month — published cap, no fair-use surprises
  • ~0.7 s latency end-to-end on Groq
  • 0 GB local RAM — works on any Mac, eventually
  • No model downloads, no API keys to manage
  • Free tier: 2,000 words/month, no card required
  • Cancel anytime via Stripe Customer Portal
Sign up free →

Same desktop app for both. Switch from local to Pro (or back) anytime from the menu bar.

How it works

Same flow for Local and Pro. Different inference, identical UX.

1. Hold the hotkey

Right Option key by default (configurable). The floating pill appears at the bottom of your screen with 16 bars rippling to your voice.

🎙

2. Talk, then release

Whisper transcribes (locally on MLX or remotely on Groq), an LLM polishes the structure — ordinals become numbered lists, fillers get removed, self-corrections get applied.

⌘V

3. Text pastes at your cursor

The polished text shows up exactly where you were typing — Slack, VS Code, Notes, Gmail, anywhere with a text field.

Side by side

When to pick which.

Susurro LocalSusurro ProWisprFlow
PriceFree, MIT$10/mo (2k free)$15/mo
Local RAM~3 GB0 GB0 GB
Latency (5s clip, M3 Pro)~1.5 s~0.7 s~1–3 s
Word cap (paid tier)100k/mo (published)"Fair use" (vague)
OfflineYesNoNo
Audio leaves your MacNeverYes (Groq · no training)Yes (proprietary)
Open sourceYes, MITYes, MIT (client)Closed
Hotkey + waveform pillYesYesYes
Smart formatting (lists, fillers, backtrack)Yes (local Llama 3B)Yes (Llama 70B)Yes

Install Susurro Local

macOS 13+ on Apple Silicon. One shell command.

$ curl -fsSL https://raw.githubusercontent.com/danilobrando/susurro/main/install.sh | bash

The installer checks for Apple Silicon, installs Python deps via pipx, downloads Whisper + Llama 3B (one-time, ~5 GB), and registers the susurro command. After install, you'll grant 3 macOS permissions and hold to talk.

FAQ

Can I switch between Local and Pro?

Yes — same app, single click in the menu bar. Susurro Pro saves a token in ~/.susurro/auth.json; signing out goes back to Local. The hotkey, waveform pill, polish prompt — all identical.

What's the deal with the 100,000 word/month cap on Pro?

Most paid dictation tools say "unlimited with fair use" and throttle you privately. We publish the cap: 100,000 words/month before a soft warning, 110,000 hard cap with a 24h cooldown. At average ~50 words per dictation that's ~2,000 dictations/month — more than even heavy daily users. If you need more, contact us.

What happens with my audio on Susurro Pro?

Audio is streamed to Groq for Whisper transcription + Llama polish, then dropped. Nothing persisted on our servers — we only store the final word count for usage metering. Groq's TOS states they don't train on API data. If you need zero-network privacy, use Susurro Local.

Why is Susurro Local Apple Silicon only?

The local backend uses Apple's MLX framework for Whisper and Llama, which only runs on M-series chips. Susurro Pro doesn't have this restriction — once we ship the Intel/Windows desktop client, you'll be able to use Pro from anywhere.

What is the "smart formatting" actually doing?

An LLM looks at the raw Whisper output and applies four kinds of edits: ordinals like "primero, segundo, tercero" become a markdown numbered list; obvious fillers (eh, mmm, you know, um, uh) get removed; self-corrections ("Pedro, eh, Pablo digo") collapse to the final intent; long monologues get paragraph breaks. It explicitly refuses to paraphrase or change the speaker's words.

How do I get a refund?

Email hi@susurro.live. We refund first-month cancellations within 7 days, no questions asked.

Can I use my own Groq / OpenAI / Anthropic key with the desktop app?

Yes — that's Susurro Local's "advanced" mode. Set SUSURRO_GROQ_API_KEY in your environment, change STT_BACKEND="groq" in susurro/config.py, and the app proxies through your own key. Free, no Susurro Pro account needed.