Comparison · Updated May 2026

Dictation,
on Apple Intelligence.

When Apple shipped Apple Intelligence with macOS 26, it quietly opened a door no one else has walked through yet: third-party apps can now use Apple Foundation Models — the on-device LLM Apple maintains as part of the OS — for any text task, including dictation cleanup. Dollop is currently the only Mac dictation app that does this, which is why it adds 0 GB of RAM, costs nothing, and runs entirely on-device. Here's the full picture.

Apple shipped a 3-billion-parameter on-device LLM as part of macOS 26 and iOS 19. The Foundation Models framework lets any app use it — for free, with no cloud routing, no per-request cost, and crucially, no separate model download. Here's what that unlocks for dictation specifically.

01
Zero RAM cost for the app

Whisper-based dictation apps load a 700 MB to 3 GB model into memory while running. Apps using Apple Foundation Models don't load anything — Apple's model lives in the OS, kept warm by the system whether or not your dictation app is running. Net new RAM cost from a dictation app: 0 GB.

02
Genuine on-device privacy

Apple's foundation model never touches the network — it runs on your Neural Engine. No request goes out, no response comes back. That's a stronger architectural privacy posture than even Whisper-based "on-device" tools, which still ship a model you have to trust the source of.

03
Cleanup that's actually tuned for dictation

Generic LLMs over-edit dictation — they smooth tone in ways the speaker didn't intend or hallucinate phrases that weren't said. Dollop trains a LoRA adapter specifically on dictation cleanup pairs (raw → cleaned), which behaves more conservatively than generic GPT polish. The adapter weighs ~150 MB and loads on top of Apple's 3B parameter model.

04
No per-request cost

Cloud-based dictation tools (Wispr Flow, Cluely) have real per-API-call costs that flow into your subscription. Foundation Models has no per-request cost because it runs on hardware you already own. That's why Dollop can be free in a way that cloud apps fundamentally can't.

05
Apple Silicon + macOS 26 required

The hard requirement: Apple Foundation Models needs Apple Silicon and macOS 26 (Tahoe) or later. Most Macs sold since 2021 qualify. Intel Macs and pre-26 macOS versions don't get access to the foundation model and can't run Dollop — Voibe or VoiceInk cover that gap.

Most comparison pages list ten features. Three of them matter when you're actually switching.

Where does the audio go?
On-device means your voice and the transcript stay on the Mac you're typing on. Cloud means audio is uploaded, transcribed remotely, and the text is downloaded back — usually with no way to know which providers see it on the way through. This is load-bearing for anyone touching client work, regulated content, or proprietary information.
How much RAM does it actually take?
The forgotten metric. "On-device" doesn't mean "free" — Whisper-based tools load 700 MB to 3 GB into memory while running. If you already have Cursor, Chrome, Slack, and a Docker container open, that matters. Apple Foundation Models is the only path right now to real on-device dictation at 0 GB.
How clean is the cleaned text?
Raw transcription is a solved problem — Whisper, Parakeet, and Apple's models are all excellent. The differentiator is what happens after: filler removal, punctuation, formatting commands, tone-matching to the active app. A tuned dictation model beats a generic LLM polish step every time.
ToolRAMAudio leaves Mac?PricingCleanup
Dollop0 GBNeverFreeTuned LoRA
Superwhisper~1.5 GBOptional$249 onceGeneric LLM
Voibe~700 MBNever$9.90/moWhisper + rules
VoiceInk~2 GBNeverFree / open-sourceOptional
MacWhisper~1–3 GBNever€64 onceFile-based
LumeVoice~700 MBNeverSubscriptionWhisper
Apple Dictation~0 GBNever (Ventura+)Free (built-in)None

RAM figures are approximate, measured at idle with the smallest model loaded. Dollop uses Apple Foundation Models — the OS keeps the model warm independently of the app, so the app itself contributes 0 GB beyond the OS baseline.

01

Dollop

Free · dollop.co
Editor's pick (us)

Dollop is the voice OS I built for the Mac. It does four things, all on-device, all free: dictation (clean text pasted at your cursor in any app), an AI chat overlay (multi-turn, optionally screen-aware) for asking questions or rewriting, Little Overlay (⌃ A — a tiny floating glass pill that hears your selection, sees your screen, and answers in place for the one-shot question that doesn’t need a chat thread), and Meeting Notes (record and transcribe lectures, calls, and meetings with summaries and action items, fully on-device). It runs on Apple Foundation Models, the on-device LLM Apple ships with macOS 26, and ships with a tuned cleanup adapter trained specifically for the way people actually speak. Because Apple already keeps the foundation model warm in the OS, Dollop contributes 0 GB to your RAM footprint. Your audio never leaves the Mac. Completely free.

What's good
  • Four pillars in one app: dictation, AI chat, Little Overlay, Meeting Notes
  • Only Mac dictation app on Apple Foundation Models
  • 0 GB RAM cost, the OS hosts the model
  • Tuned cleanup adapter, not a generic polish step
  • Meeting Notes: record + transcribe + summarize on-device
  • Per-app tone (Casual / Formal / Excited)
  • Completely free, no subscription, no premium tier
What to know
  • Apple Silicon + macOS 26 only, no Intel, no Windows
  • Apple Intelligence must be enabled
  • New product, smaller community than Wispr or Superwhisper
02

Apple Dictation

Free (built-in)
Apple's own

Built into macOS Ventura and later. Uses Apple's speech recognition, fully on-device for supported languages on Apple Silicon. Doesn't yet use Foundation Models for cleanup — Apple Dictation is transcription-only, no filler removal, no formatting commands. Dollop adds the Foundation Models cleanup layer on top of the same Apple-native foundation.

03

Superwhisper

$249 once · superwhisper.com

Doesn't use Apple Foundation Models — runs its own Whisper model locally (~1.5 GB RAM). $249 one-time. The mature pick before Dollop existed. Cross-platform (Mac/Windows/iOS) by virtue of not being Apple-exclusive.

04

Voibe

$9.90/mo · getvoibe.com

Whisper-based, $9.90/month. Strong privacy positioning but doesn't tap Apple Foundation Models — still loads ~700 MB of Whisper into memory.

05

VoiceInk

Free / open-source

Open-source Whisper-based dictation. Free. Doesn't use Foundation Models but is auditable and works on older Macs.

06

Wispr Flow

$15/mo · wisprflow.ai

Cloud-based — sends your audio to remote servers and processes it through OpenAI / Anthropic / Cerebras LLMs. Doesn't use Apple Foundation Models. $15/month.

What to know
  • Audio leaves your Mac
  • $15/mo subscription
  • Privacy crisis in early 2026
If RAM is tight on your Mac …
Dollop — 0 GB resident, the OS hosts the model.
If you want zero subscription, ever …
Dollop — completely free, no premium tier.
If your work is sensitive and audio cannot leave the Mac …
Dollop — fully on-device, no cloud at any step.
If you live in Cursor, VS Code, Slack, Linear, Mail …
Dollop — per-app tone (Casual / Formal / Excited).
If you want cleanup that's actually tuned for dictation …
Dollop — the only one with a LoRA finetuned for it.
If casual is enough and you don't want a new app …
Dollop — installs in 30 seconds and stays out of the way.

Hard requirement: Dollop runs on Apple Silicon Macs with macOS 26 or later. Most Macs sold since 2021 qualify. If you're on Intel, that's the constraint to plan around.

What is Apple Foundation Models?
Apple Foundation Models is the on-device LLM Apple ships as part of macOS 26 (and iOS 19). It's a 3-billion-parameter model that runs on the Neural Engine of Apple Silicon chips. Apple opened a developer framework — also called Foundation Models — that lets third-party apps use the model for free, with no cloud routing and no per-request cost. Dollop is the first Mac dictation app to use it.
How is Apple Foundation Models different from Apple Intelligence?
Apple Intelligence is the umbrella brand for Apple's on-device AI features (Writing Tools, Image Playground, smarter Siri, etc.). Foundation Models is the developer-facing framework that gives third-party apps access to the underlying on-device LLM that powers Apple Intelligence. Same model, different layer of the stack.
Why doesn't Apple Dictation use Apple Foundation Models for cleanup?
Apple Dictation predates the Foundation Models framework — it's been part of macOS since long before Apple Intelligence. Apple has signaled that future dictation enhancements will land later in 2026, which may include cleanup. Dollop shipped this integration in 2026 because the Foundation Models framework opened up the access for third parties.
Does Dollop work without Apple Intelligence enabled?
No. Dollop's cleanup pass uses Apple Foundation Models, which requires Apple Intelligence to be on. The first launch onboarding walks you through enabling Apple Intelligence in System Settings if it's not on yet. Once enabled, the model stays warm and Dollop uses it without any additional setup.
What does Dollop actually do?
Four things, all on-device. (1) Dictation: hold ⌥ Space, talk, and clean text appears at your cursor in any app. (2) AI chat: hit ⌃ S to summon a floating chat overlay, optionally screen-aware so it can answer questions about your active window. (3) Little Overlay: hit ⌃ A for a tiny floating glass pill — the smallest surface — that hears your selection, sees your screen, and answers in place for the one-shot question that doesn't need a chat thread. (4) Meeting Notes: record any class, call, or meeting; Dollop transcribes, summarizes, and pulls action items, all locally on your Mac.
How much does Dollop cost?
Free. No credit card, no trial, no premium tier. Dictation, AI chat, Little Overlay, and Meeting Notes are all unlocked from the moment you download.
Does Dollop work without an internet connection?
Yes. Dictation, the chat overlay, and Meeting Notes (recording, transcription, and summarization) all run on-device on Apple Silicon. Your audio never leaves your Mac. The app does check for software updates over the network, but the core features work offline, on a plane, in a SCIF, in a basement seminar room, anywhere.
Can Dollop record and transcribe meetings or lectures?
Yes, that is what Meeting Notes does. Hit record before a class, Zoom call, or in-person meeting; Dollop captures audio (via system audio capture or your mic), transcribes it on-device, and produces a clean summary with action items. Everything stays on your Mac.
Will Dollop work on Intel Macs?
No, Dollop uses Apple Foundation Models, which require Apple Silicon and macOS 26 or later. Most Macs sold since 2021 qualify. If you are still on Intel, that is the upgrade to plan around; the rest of this guide assumes you are on Apple Silicon.
Can I dictate into Cursor, VS Code, Slack, and other apps?
Yes. Dollop pastes the cleaned text wherever your cursor is. There is no per-app setup. You can also assign different writing tones (Casual, Formal, Excited) to different apps so dictation in Slack reads casually and dictation in Mail reads formally.
Will more dictation apps use Apple Foundation Models?
Probably, given the architectural advantages (0 GB RAM, no per-request cost, in-OS privacy guarantee). As of mid-2026, Dollop is the only one shipping. Wispr Flow's cloud-routing architecture and the Whisper-based apps' cross-platform commitments make it harder for them to switch. The advantage compounds while it lasts.
How much faster is dictation on Apple Foundation Models vs Whisper?
For the transcription step itself, Apple's speech recognition and Whisper are both excellent — both run on the Neural Engine, both produce results in 100–300 ms for typical dictations. The speed difference comes from cleanup: Apple Foundation Models stays warm in the OS, so the cleanup pass starts immediately. Whisper-based apps with a separate cleanup LLM have to load that LLM too, adding setup latency on first run.

Apple Intelligence opened up a category that didn't exist before: third-party apps that ride on Apple's foundation model instead of shipping their own. Dollop is currently the only Mac dictation app doing it — which is why it can be free, on-device, and 0 GB of RAM, all at the same time.

If you're on an Apple Silicon Mac with macOS 26 and Apple Intelligence is on, Dollop is the dictation app that fits the platform best. If not, the older alternatives still work — they just don't get the architectural benefits Apple Foundation Models provides.

Get Dollop — free
Completely free. No credit card, no premium tier. macOS 26+, Apple Silicon.