Voice-first personal AI agents with continuous memory across voice and text — four distinct personalities, ultra-low latency, free on iOS.
Free
Summary
Voice dictation that works in every app and cleans up as you speak — no filler words, correct formatting, right tone.
Screenshots
Description
Wispr Flow is a dictation tool that runs system-wide. Hold a key, speak, release, and polished text appears in whatever application has focus — an email, a code editor, a Slack message, a document.
What makes it different from built-in dictation
- It edits while it transcribes. Filler words, false starts, and self-corrections are removed, so "um, send it to, no wait, send it to Priya" becomes "Send it to Priya."
- Context awareness. It adapts formatting to the app you are in — bullet points in a doc, terse phrasing in a chat window, correct casing for code identifiers.
- A personal dictionary that learns names, jargon, and product terms from your usage.
- Command mode for editing what you just dictated by voice.
- Many languages, including switching mid-sentence.
Why people keep it
Most people speak far faster than they type, and the gap widens for long-form writing. The cleanup step is what makes the output usable without a rewrite, which is where earlier dictation tools failed.
Available for macOS, Windows, and iOS, with a free tier of weekly words and a subscription for unlimited use.
Reviews
Similar App Suggestions
Local-first meeting and interview recorder that transcribes, labels speakers and writes up your notes entirely on your own computer, for a one-time price.
Paid
Local-first Mac dictation that types into any app, plus file and link transcription across 110 spoken languages on Apple Silicon.
Freemium
Privacy-first voice to text for macOS, Windows, and iOS — runs offline on-device with customisable AI modes.
Freemium
High-quality stem separation — split any track into vocals, drums, bass, and instruments with minimal artefacts.
Freemium