Wispr Flow
Popular voice dictation that types cleaned-up text in any app; free for 2,000 words a week, Pro $15/month.
Should you use it?
Pick it if
People who write a lot of email, messages or notes and would rather talk than type.
Best for: People who write lots of email and messages and would rather talk (AI apps Top 20)
Skip it if
You need dictation that never leaves your computer; VoiceInk or MacWhisper run models locally.
You give up: Needs the internet, with no on-device option; training default not stated
The short version
- What this is
- A dictation app that turns what you say into clean, punctuated text in whatever app you are typing in.
- Why it matters
- Dictation can save time over typing; this app cleans up filler words and punctuation as you speak, in any app s3.
- Free for 2,000 words a week on desktop; Pro $15/month or $12 billed yearly s1.
- Latest update, 17 Sep 2026: Canto, Wispr's first own speech model s4.
- Turn off model training in Settings > Data and Privacy if you want s2.
Good at
Our take
Wispr Flow is dictation that tidies up as it goes: it drops "um"s, adds punctuation and formats the text, in any app s3. The free plan is enough to see if it suits you, at 2,000 words a week on a computer s1.
Everything you say is sent to Wispr's servers to be transcribed s2. Audio is discarded after transcription unless you turn on cloud storage, and you can switch off model training in settings s2. If you want dictation that stays on your machine, look at VoiceInk or MacWhisper instead. Wispr says it now uses Canto, its own speech model s4; there is no independent accuracy test of it yet, so we haven't scored Flow.
Not scored yet
This is a First look: the call above comes from the maker's own pages, so there is no score yet. When an independent accuracy test of Flow or its Canto speech model from the last 90 days is published.
VoiceWriting
New to this? What the scores and labels mean
- 0 to 100
- Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
- Our verdict
- Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
- First look
- Just released. We say what it is and whether to bother, and give it a score once public results exist.
- No score yet
- None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
- Best buy
- Nothing cheaper scores as well for that job.
- Best free
- The best score for that job that costs nothing, through a free plan or by running on your own computer.
- Pay as you go
- No monthly plan: you pay for each use, usually through a developer account.
- Checked
- The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
- AI model
- The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
- Open source
- Free to download and run on your own computer, so nothing leaves your machine.
Alternatives
Nothing we have scored beats it for voice on score or on price.
- MAI-Transcribe-2Voice model–Pay as you goSpeech-to-text model, 3rd of 55 on Artificial Analysis, for developers who want an API. Side by side
Evidence
Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.
How we scored this
Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.
No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score
Sources 4
Something here out of date or wrong? Report a mistake and we will check it against the source.
History 2 changes
Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.
- First look. No independent accuracy test, so not rated.
- Audit: removed an unsourced claim about how widely known it is.
Use it well 3 guides on this site
Pages on this site that help with the jobs above.