Voice dictation
for VS Code.
VS Code with voice dictation is the longest-running productivity hack in the dev world — comments, commit messages, Copilot prompts, even literal code via natural language. The friction has always been finding a Mac dictation app that doesn't fight VS Code for memory, doesn't auto-correct camelCase identifiers, and works inside the editor's quirky text fields. Dollop covers all three: free, on-device, 0 GB of RAM, with cleanup that respects how developers actually dictate.
Voice typing in VS Code has its own UX rules that most general-purpose dictation tools don't think about.
VS Code uses Electron — its text inputs aren't standard macOS text fields, which trips up some dictation tools. Dollop uses Accessibility APIs to paste into any focused text field, including the editor itself, the terminal, the Copilot Chat panel, the search bar, and extension panels.
VS Code is already an Electron app — Chromium plus Node, hundreds of MB of memory before you open a single file. Pairing it with Whisper-based dictation tools (700 MB to 3 GB) puts pressure on 16 GB Macs. Apple Foundation Models lives in the OS so Dollop contributes 0 GB.
Generic LLM cleanup will "fix" useState() to "use state" and break camelCase. Dollop's tuned LoRA preserves identifiers because it was trained on dictation pairs — including code-adjacent prose where developers literally say "useState" out loud.
VS Code's default keybindings are dense. Dollop's defaults (hold-fn for push-to-talk, ⌘ Space for toggle) don't conflict with any common VS Code shortcut. Both are remappable if you've already claimed those.
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 |
|---|---|---|---|---|---|
| Works in VS Code Electron text fields | ● | ● | ● | ◐ | ◐ |
| Preserves camelCase / snake_case | ● | ◐ | ◐ | ○ | ○ |
| RAM cost | 0 GB | ~1.5 GB | ~700 MB | ~1-2 GB | 0 GB |
| Price | Free | $249 | $15/mo | Free | Free |
| On-device (no upload of code) | ● | ◐ | ○ | ● | ◐ |
| Custom code vocabulary | ● | ● | ● | ◐ | ◐ |
● Yes · ◐ Partial · ○ No. Verified May 2026.
A short list of friction points specific to this app, and the fix for each. We use Dollop in this app daily; these are observed, not invented.
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
Mature commercial pick. $249 one-time, ~1.5 GB RAM, works in VS Code like any Mac app. The RAM cost matters more here than in lighter editors.
- $249 up front
- 1–3 GB RAM alongside VS Code
- Generic LLM polish
VoiceInk
Open-source, free, runs Whisper locally. Auditable. Same RAM concern as Superwhisper but no subscription.
Voibe
Subscription dictation, $9.90/month. Works in VS Code's text fields. Lighter Whisper model than Superwhisper (~700 MB).
Wispr Flow
Cloud dictation, $15/month. Fast UX but ships your code-adjacent prompts to OpenAI / Anthropic / Cerebras. Privacy crisis in early 2026.
- Code context leaves your Mac
- $15/mo
- 2.7 Trustpilot
Apple Dictation
Built into macOS, works in VS Code's text fields. No cleanup, no formatting commands — but if you just want to throw thoughts at Copilot Chat and edit, it's free.
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.
Does dictation work in VS Code's Copilot Chat / inline AI?
Will dictation mess up my code formatting?
Can I dictate actual code, not just comments?
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?
How do I add code-specific vocabulary?
Does Dollop work with VS Code on Linux or Windows?
For VS Code dictation on a Mac in 2026, Dollop is the answer. Free, on-device, 0 GB of RAM, with a cleanup adapter that respects identifiers and doesn't fight Electron for memory.
If you're on an older Mac without Apple Intelligence, Superwhisper is the safest commercial pick. The Whisper RAM cost matters more here than in lighter apps — keep an eye on Activity Monitor.