Tool · Voice and speech

MacWhisper

A Mac app that turns recordings, videos and meetings into text on your own computer, so audio need not leave your Mac. It can also make subtitles, translate and take dictation. Free version, or a one-off Pro licence.

Go to MacWhisper’s website

At a glance

Open or closed: Closed
Only usable through the maker's app or API
Paid closed app; the speech models it runs (Whisper, Parakeet) are open.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Can I sell what I make?: The terms don't say clearly
Terms at macwhisper.com/legal/terms were not read. Transcripts are made locally from your own recordings.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
Cost: Free option: Free forever version
Plans below.
How you use it: Desktop app, On your own computer, Bring your own AI key, Phone app
Runs Whisper/Parakeet on-device; optional cloud services via your own keys (OpenAI, Deepgram, ElevenLabs, Groq and others). FAQ mentions an iOS/iPad version without details. Has a CLI.
source · checked 12 Oct 2026 · checked on the maker's own page
Skill needed: No setup
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: Good Snooze (NL)
Site says it is built at Good Snooze in the Netherlands; sold via Gumroad (goodsnooze) and the App Store.
source · checked 12 Oct 2026 · checked on the maker's own page
Status: Available
source · checked 12 Oct 2026 · checked on the maker's own page

What you can make with it

A voice or speech, text from a recording (main use)
A voice or speech, a written translation of a recording

audio to textvideo to text

Also dictation, meeting recording, subtitles and AI summaries (no separate task ids).

source · checked 12 Oct 2026 · checked on the maker's own page

Plans and prices

Plan	Price	Includes
Free	Free
Pro	€64 one-off	Per licence, lifetime updates

Which features are Free vs Pro was not readable. Cloud models need your own API keys (paid to those providers). App Store version may differ.

source · checked 12 Oct 2026 · checked on the maker's own page

Models it uses

Whisper, NVIDIA Parakeet

Models it uses (not yet listed on Plainly)

Qwen (speech models)

Other options for “A voice or speech, text from a recording”

Adobe Podcast (Enhance Speech), Adobe Premiere, AssemblyAI, Async (formerly Podcastle), AudioShake, Auphonic, Azure AI Speech, CAMB.AI, Cartesia, Cleanvoice AI, Clipchamp, Deepgram, Descript, Distil-Whisper, Dubverse, ElevenLabs, Filmora, Gling, Happy Scribe, Hugging Face, Kapwing, Krisp, MiniMax Audio, Narakeet

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.