Speechy vs Spokenly
Spokenly gives you free local dictation and leans on cloud models and AI keys for the rest. Speechy keeps everything on your Mac, cleans up your words with no AI setup, ignores other voices and answers your coding agents from the notch.
Spokenly is free for unlimited local dictation, and that is hard to argue with. So here is what Speechy does that you might still pay for, with real examples.
At a glance
| Speechy | Spokenly | |
|---|---|---|
| Where your voice is transcribed | Always on your Mac | Cloud models by default, local models optional |
| Cleaning up ums and corrections | Built in, on your Mac | Through AI: Pro, Apple Intelligence, your own key, or a new local model |
| Ignores other people's voices | Yes, with Only My Voice | No |
| Claude Code and Codex | Questions, permissions and plan limits in your notch | Agents can ask you questions over MCP |
| Price | Lifetime from $99, or Pro at $12.99 a month | Free locally, $19 once for extras, Pro at $9.99 a month |
| Platforms | Mac with Apple silicon | Mac, Windows, Linux, iPhone and iPad |
On your Mac, always
Spokenly's own docs say it uses cloud models by default, with local models as optional downloads. Pro audio passes through Spokenly's servers, and AI instructions can send your text to a cloud model.
Speechy has no cloud transcription at all. All 15 of its speech models run on your Mac's chip, and your dictation is never sent to a cloud AI.
Speechy's Models page, listing on-device voice models from NVIDIA, Apple and Whisper
Clean text, no AI key
In Spokenly, cleanup comes from AI: hosted on Pro, Apple Intelligence, your own key, or a new local cleanup model that is off by default.
Speechy tidies your words on your Mac as soon as you install it, with no account at an AI company and no API key. Every "Speechy types" box on this page is the app's own output for that sentence, taken from Speechy's test suite.
It keeps up when you change your mind, too. Say "sorry", "I mean", "make it" or "or rather", and Speechy swaps the old time, date, amount or name for the new one. "Make it work" and "sorry I'm late" are left alone.
Only your voice gets typed
Spokenly separates speakers when it transcribes a meeting or a file, but nothing leaves other voices out while you dictate. Speechy's Only My Voice learns your voice from one sentence read aloud, then drops words from the colleague behind you, the TV or a speakerphone, and keeps learning as you use it. Someone talking over you at the same moment can still slip through, but everyday background chatter does not.
Only My Voice: read one sentence aloud and Speechy learns your voice
Built for Claude Code and Codex
Spokenly has an MCP server so Claude Code, Codex and Cursor can ask you a question and you answer by voice. Speechy goes further, in your Mac's notch:
- Answer everything in one place. Questions, permission requests, plans and finished tasks all land in the notch. Press 1 to allow or 2 to deny, J and K to move between them and E to clear one. Answered too fast? Esc takes it back within 2 seconds.
- Watch your plan limits. Your Claude and Codex usage sits beside the camera, read straight from the tools, with no keys to paste. The Usage tab shows the 5 hour and weekly windows.
- Start the conversation. Say "api, run the migration again on staging", and it goes to that project's agent.
- Read replies right there. Replies show formatted, with tables and code. Drop in up to 6 images, or drag the corner to make the chat bigger.
- Name files out loud. Turn on Reference coding files, and the file names you say become @file references in Claude Code for VS Code.
A Codex permission request in Speechy's notch, with Allow and Deny
Claude and Codex plan usage beside the camera
Talking to the api agent from Speechy's notch
Everything else Speechy does
Several languages, one dictation
Pick your languages and turn on Multiple languages in one dictation. Speechy works out the language again after every pause, on your Mac.
With Hindi and English picked. Speechy mixes English, Spanish, French, German, Italian, Portuguese, Dutch, Hindi, Japanese and Chinese.
Speechy's language settings, with Multiple languages in one dictation
Lists, without touching the keyboard
Count your points out loud, or say "bullet", and Speechy writes the list. In Mail, Notes, Pages and Word the dashes become bullets.
Numbers, money and times, written properly
Punctuation and new lines when you ask
Emails come out shaped like emails
Start with a greeting and end with a sign-off, and Speechy puts each on its own line. It skips this in chat apps, terminals and code editors.
Your words, spelled your way
Add names and jargon to your dictionary, fix a word Speechy keeps mishearing with a replacement (in every app, or only in one), and save snippets for things you say often. Say "insert" and the snippet's name.
With a snippet called "my address" saved.
Speechy's dictionary: words, replacements and voice snippets
It spells what is on your screen
With App Context on, the names in the window you are dictating into become spelling hints. It stays on your Mac, password fields are always skipped, and you can leave out any app.
With DictationController.swift on screen.
Context you control: the names Speechy used from your screen, and the apps it leaves out
Undo a dictation, or throw one away
Press ⌘⌥Z within five minutes and Speechy removes the last dictation and puts back anything it replaced. Press ⌘Esc while talking to drop the take, so nothing is typed or saved.
Speechy's shortcuts: Fn to dictate, ⌘⌥Z to undo, ⌘Esc to discard
Paste, type or just copy, and send
Speechy pastes by default, then puts your clipboard back the way it was. It can type the words out instead, or leave them on the clipboard. Turn on Auto submit and it presses Enter (or ⌘Enter) for you.
Speechy's output settings: paste method, clipboard and auto submit
And more
- Four recording styles: a compact pill, a wide pill with your words, a Dynamic Island style bar or a one-line ticker.
- Music pauses while you talk, then carries on, with Background audio set to Pause media.
- Help when the mic is wrong: if Speechy hears nothing, it plays your recording back and opens the microphone picker in one click.
- Stats for your speed, streaks, golden hour and time saved, and a Speechy pass you can share.
- Light on memory: models free about 1.2 GB after 15 minutes idle and reload as you start talking.
- A whole email from one sentence with Smart Polish on: "draft an email to Sarah saying the deck is delayed to Thursday".
Where Spokenly is better
- Free. Unlimited local dictation costs nothing. Speechy has no free plan.
- Every platform. Mac, Windows, Linux, iPhone and iPad. Speechy is Mac only for now.
- More engines. Many local and cloud models, with your own keys for free.
- Meetings and files. It records meetings without a bot and transcribes files with speaker labels.
- Work Macs. A Local Only Mode that companies can enforce, plus team seats.
The short version
If free local dictation is all you need, Spokenly is a great deal. Choose Speechy if you want everything on your Mac by default, clean text without setting up AI, other voices left out, and your coding agents in the notch. See pricing.
Spokenly details checked on 14 October 2026 on its pricing page, privacy policy and agent docs. Spokenly updates almost daily, so check their site before you decide.