Voice dictation
for Cursor.
Cursor rewards long, descriptive prompts — the kind that take 30 seconds to type and 8 seconds to dictate. The problem is dictation tools that ship your code-prompt to the cloud (Wispr Flow), eat 1.5 GB of RAM you'd rather give Cursor (Superwhisper), or auto-format your prose in ways that mangle technical terms. Dollop solves all three: free, on-device, 0 GB of RAM, with a tuned cleanup adapter that respects code identifiers, framework names, and the way developers actually talk to AI.
Cursor users have a specific dictation profile — long prompts, technical vocabulary, intermittent bursts rather than steady flow. Most dictation apps optimize for the wrong things.
Cursor is already a memory-heavy app. Pairing it with a dictation tool that loads 1–3 GB of Whisper weights makes 16 GB Macs grind. Apple Foundation Models lives in the OS, so Dollop adds nothing — Cursor keeps the RAM it needs.
Generic LLM cleanup will "correct" useState to "use state" and React.FC to "react fc." A LoRA tuned on dictation pairs (where developers dictate code-adjacent text) preserves identifiers. Dollop's cleanup adapter is trained for this; generic cleanup steps aren't.
Brand names, framework names, your team's internal names — all of them need to spell correctly from the first dictation. Dollop's vocabulary list is matched against the cleanup pass, so "Tanstack Query" stops becoming "Tan stack query" after you add it once.
Dictation in Cursor should read like a technical spec, not a Slack message. Dollop lets you set Cursor's tone to Formal — periods, full sentences, no chat shorthand — while leaving Slack on Casual. One dictation app, two tone profiles, zero manual switching.
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.
| Tool | RAM | Audio leaves Mac? | Pricing | Cleanup |
|---|---|---|---|---|
| Dollop | 0 GB | Never | Free | Tuned LoRA |
| Superwhisper | ~1.5 GB | Optional | $249 once | Generic LLM |
| Voibe | ~700 MB | Never | $9.90/mo | Whisper + rules |
| VoiceInk | ~2 GB | Never | Free / open-source | Optional |
| MacWhisper | ~1–3 GB | Never | €64 once | File-based |
| LumeVoice | ~700 MB | Never | Subscription | Whisper |
| Apple Dictation | ~0 GB | Never (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.
| Feature | Dollop | Superwhisper | wisprflow | VoiceInk | apple |
|---|---|---|---|---|---|
| On-device (no cloud upload) | ● | ● | ○ | ● | ◐ |
| RAM cost | 0 GB | ~1.5 GB | ~700 MB | ~1-2 GB | 0 GB |
| Price | Free | $249 | $15/mo | Free | Free |
| Tuned cleanup adapter | ● | ◐ | ● | ○ | ○ |
| Per-app tone matching | ● | ○ | ◐ | ○ | ○ |
| Custom vocabulary | ● | ● | ● | ◐ | ◐ |
| Works in Cursor specifically | ● | ● | ● | ● | ◐ |
● Yes · ◐ Partial · ○ No. Verified May 2026.
Dollop
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.
- 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
- Apple Silicon + macOS 26 only, no Intel, no Windows
- Apple Intelligence must be enabled
- New product, smaller community than Wispr or Superwhisper
Superwhisper
Polished commercial alternative. $249 one-time, ~1.5 GB RAM, cross-platform. Works in Cursor like any other Mac app — but the RAM cost is real when Cursor is also open.
- $249 up front
- 1–3 GB RAM resident with Cursor open
- Generic LLM polish
VoiceInk
Free, open-source, 100+ languages, runs Whisper locally. Auditable code, no subscription. RAM cost still applies.
Voibe
Subscription dictation, $9.90/month, sub-300ms latency. Works in any text field including Cursor's prompt input.
Wispr Flow
Cloud dictation, $15/month. Fast UX but ships your prompts to OpenAI / Anthropic / Cerebras — questionable when the prompt itself contains proprietary code context.
- Audio + prompt context leaves your Mac
- $15/mo
- Privacy crisis in early 2026
Apple Dictation
Built into macOS. Works in Cursor's prompt field. No cleanup, no formatting commands — but if you just want to throw thoughts at Cursor and edit them down, it's free and zero-setup.
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's the best dictation app for Cursor?
Will dictation interfere with Cursor's own voice features?
How do I keep code identifiers spelled correctly?
What does Dollop actually do?
How much does Dollop cost?
Does Dollop work without an internet connection?
Can Dollop record and transcribe meetings or lectures?
Will Dollop work on Intel Macs?
Can I dictate into Cursor, VS Code, Slack, and other apps?
Does Dollop work in Cursor's composer / chat panel?
Can I dictate code itself, not just prompts?
If you're prompting Cursor by voice, Dollop is the obvious pick. Free, on-device, 0 GB of RAM, with cleanup tuned for the way developers dictate. Cursor keeps the memory it needs; you stop fighting your Mac to type prompts faster than your fingers can.
If you're not yet on Apple Silicon + macOS 26, Superwhisper is the established commercial alternative and VoiceInk is the free one. Either way, dictation in 2026 is the productivity unlock for AI-first coding.