Voice dictation
for Slack.
Slack rewards short, casual, lowercase messages. Most dictation apps want to capitalize every sentence, end every line with a period, and make you sound like a press release. Cloud-based ones (Wispr Flow) also send your team conversations to a third-party AI provider — not great for any company that takes IP seriously. Dollop nails the Slack tone (per-app casual mode), keeps everything on your Mac, and costs nothing.
Dictating into Slack is its own thing. The cleanup model needs to read the room — short, casual, occasionally lowercase, sometimes with deliberately broken punctuation. Most dictation apps fight this.
Slack and Mail need opposite cleanup behavior. Slack: lowercase, contractions, drop the period on short messages. Mail: full sentences, proper capitalization, signed off. Dollop lets you assign Casual to Slack and Formal to Mail, so the cleanup pass auto-adjusts based on the active app.
Cloud-based dictation tools send your audio to OpenAI, Anthropic, and Cerebras. Most companies have policies against routing work conversations through third-party AI providers — and most people don't realize their dictation tool is doing it. On-device tools sidestep the issue entirely.
Your teammates' names, channel names, project codenames — all of them need to spell correctly without manual correction every time. Dollop's vocabulary list handles this; cloud LLMs guess based on training data and miss anything your team made up.
Saying "scheduling link" to expand to your Calendly URL, or "team standup" to drop a templated standup message, makes dictation 2x faster for repeat replies. Dollop matches snippets before the cleanup pass; most other tools don't have this layer.
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 | wisprflow | Superwhisper | VoiceInk | apple |
|---|---|---|---|---|---|
| Casual tone in Slack auto | ● | ◐ | ○ | ○ | ○ |
| Formal tone in Mail auto | ● | ◐ | ○ | ○ | ○ |
| On-device | ● | ○ | ● | ● | ◐ |
| Price | Free | $15/mo | $249 | Free | Free |
| RAM | 0 GB | ~700 MB | ~1.5 GB | ~1-2 GB | 0 GB |
| Channel mentions / emoji shortcuts | ◐ | ◐ | ◐ | ○ | ○ |
● 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
Voibe
Subscription dictation, $9.90/month, sub-300ms latency, 100% on-device. Works in Slack like any Mac text field. No per-app tone matching — same cleanup style everywhere.
Apple Dictation
Built into macOS Ventura+. Free, on-device. Works in Slack — but transcribes verbatim, including fillers and missing punctuation. Dollop adds the cleanup and per-app tone Apple Dictation doesn't have, also for free.
Superwhisper
$249 one-time, ~1.5 GB RAM. Works in Slack. Generic LLM polish doesn't tone-match per-app — same dictation style in Slack and Mail.
VoiceInk
Free, open-source, runs Whisper locally. Works in Slack but requires more setup than Dollop to configure cleanup.
Wispr Flow
Cloud dictation, $15/month. Routes Slack messages through OpenAI / Anthropic / Cerebras. Most companies' security teams will not be fans.
- Audio + message context leaves your Mac
- $15/mo
- Privacy concerns for work IP
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 Slack on Mac?
Is dictating Slack messages a privacy risk?
How do I make dictation match Slack's casual tone?
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?
Can I dictate into Slack threads, DMs, and the search bar?
Does Dollop handle channel mentions and emoji?
For Slack dictation on Mac, Dollop is the right pick. Free, on-device, with per-app Casual tone matching that gets the Slack register exactly right. No more dictation that reads like a memo when you wanted to send "yeah lmk."
If your team's security policy forbids routing work conversations through third-party AI, on-device tools are the only acceptable option — Dollop is the lightest of them.