Kviskr
Last ned

Kviskr for Mac

Drag in an interview or press Start meeting. Kviskr turns Norwegian speech into text with speakers and timestamps, locally, without uploading the audio.

See how it works

Norsk

Last updated

Short answer

Norwegian audio in, text out, on your Mac.

Kviskr is a Mac app that transcribes Norwegian audio files and meetings locally, with NB-Whisper, the speech model from the National Library of Norway. You drag in an interview, a lecture or a voice memo, or record a meeting, and get the text with speakers and a timestamp for each line. The speech recognition and the speaker separation run on your Mac, so the audio is never uploaded, and it works offline. You choose bokmål or nynorsk as the written standard. The app itself is in Norwegian only.

  • Audio formats

    How it works in Kviskr
    Files macOS can read, such as WAV, MP3, M4A, AAC, AIFF and FLAC. The original is not changed

  • Video

    How it works in Kviskr
    Not supported. Extract the audio first, for example in QuickTime Player

  • Length

    How it works in Kviskr
    No fixed limit. Long files take longer, depending on your Mac

  • Speakers

    How it works in Kviskr
    Detected locally when Kviskr hears at least two voices. Rename them as you like

  • Timestamps

    How it works in Kviskr
    Each line has a timestamp in the app. Copied text has names, not timestamps

  • Written output

    How it works in Kviskr
    Bokmål or nynorsk, which you choose. English with the same models

  • Export

    How it works in Kviskr
    Copy the text, or export recordings as a plain-text file. No Word or subtitle export

  • Internet

    How it works in Kviskr
    Not needed. The standard Norwegian model and the speaker models come with the app

  • Storage

    How it works in Kviskr
    Audio and text stay on your Mac and are deleted after 30 days unless you change it

  • Requirements

    How it works in Kviskr
    A Mac with Apple silicon (M1 or later) and macOS 15.1 or later. The app is in Norwegian

Three steps

From recording to text.

  1. 01

    Drag in the audio file

    Drop the file on the Kviskr window, click Importer lydfil (Import audio file) under Opptak (Recordings), or right-click the file in Finder and choose Open With → Kviskr. You can add several files at once.

  2. 02

    Let the Mac do the work

    Files wait in a queue and are transcribed one at a time. NB-Whisper turns the Norwegian speech into text on your Mac, and Kviskr finds the speakers in the same pass. The file is not uploaded anywhere.

  3. 03

    Show speakers, name them, copy

    Turn on Vis talere (Show speakers) to see each line with a speaker and a timestamp. Rename Taler 1 and Taler 2 to real names or pseudonyms, then copy the text or export it as a plain-text file.

An imported audio file in Kviskr, in Norwegian, with sample data: «Intervju med kunden» (Interview with the client) with the speakers Kari and Ola, and each line with a name and a timestamp, such as Kari 00:00 and Ola 00:07

Norwegian meeting transcription

From Kviskr 0.7.0 you can record a meeting directly. Press Start møte (Start meeting) under Opptak or in the menu bar, and press Stopp when you are done. Kviskr transcribes the meeting and separates the speakers on your Mac. No bot joins the call, and nothing is sent to a meeting service.

  • Meetings in a room are recorded with the microphone.
  • For video calls there is a setting, Ta med lyd fra Macen (Include audio from the Mac), that also records what the Mac plays. It is new in 0.7.0, so make a short test recording with your own headset and call app before an important meeting.
  • Voices are not remembered between meetings, so you name the speakers each time.
  • Kviskr does not write the summary. You get the full transcript.

Tell the others that you are recording. Kviskr shows that reminder the first time you start a meeting. More, in Norwegian: Transkriber møter på norsk.

A meeting in Kviskr 0.7.0, in Norwegian, with sample data: the meeting «Planlegging av høstlanseringen» (Planning the autumn launch) with the speakers Kari, Ola and Taler 3, and lines with names and timestamps

How accurate is it on Norwegian?

NB-Whisper was trained by the National Library of Norway on around 66,000 hours of Norwegian speech. Its paper reports a 2.2% word error rate for NB-Whisper Large on read bokmål in the NST dataset, against 6.8% for OpenAI's Whisper Large-v3. Read speech is the easy case. Free conversation is harder, and in our own measurements most of the difference is words that get left out when people talk fast, quietly or over each other.

Kviskr has measured its own models on public Norwegian test sets. The table shows how many words out of 100 were left out. Standard is the model that comes with the app. Ekko (beta) is Kviskr's own model, trained further from NB-Whisper Large, and can be downloaded from 0.7.0.

  • NB Samtale: free conversation (500 clips)

    Words left out, Standard
    21.2
    Words left out, Ekko (beta)
    10.2

  • NB Tale: spontaneous speech, all regions (302 clips)

    Words left out, Standard
    4.5
    Words left out, Ekko (beta)
    1.8

  • NorGovPCC: government press conferences (200 clips)

    Words left out, Standard
    17.6
    Words left out, Ekko (beta)
    5.0

Per 100 words in the reference, lower is better. Ekko gets slightly more words wrong in free conversation (8.9 against 7.4 per 100), because it writes down words Standard skips. Measured 11 October 2026. Full method and all five test sets, in Norwegian: kviskr.no/metode.

Bokmål, nynorsk and dialects

Norwegian has two written standards, and the speech model cannot tell from the audio which one you want. You choose Norsk (bokmål) or Norsk (nynorsk) in the settings or the menu bar, and Kviskr writes in that standard whatever dialect is spoken. Nynorsk in free conversation is the hardest case we have measured: on the 124 nynorsk clips in NB Samtale, Standard left out 24.3 of 100 words and got 10.3 wrong, against 21.2 and 7.4 for the whole test set. Names and technical terms that keep coming out wrong can go in the vocabulary (Ordbok).

Other ways to transcribe Norwegian

Several good services transcribe Norwegian, and some use the same speech model as Kviskr. The main difference is where the audio goes and who may use the service. At the University of Oslo, Autotekst runs on the university's own servers. At NTNU, Speech to text is for public and internal data only. Jojo from the newspaper VG is local like Kviskr. transkribere.no and TurboScribe are cloud services you upload to.

  • Kviskr

    Where the audio is processed
    On your Mac
    Who can use it
    Anyone with an Apple silicon Mac
    Speech model
    NB-Whisper, Ekko (beta)

  • Autotekst (University of Oslo)

    Where the audio is processed
    UiO servers, approved up to red (confidential) data
    Who can use it
    UiO staff and students; other non-commercial organisations can buy access
    Speech model
    NB-Whisper or OpenAI Whisper

  • Speech to text (NTNU)

    Where the audio is processed
    NTNU service, public and internal data only
    Who can use it
    NTNU users, on the NTNU network or VPN
    Speech model
    NB-Whisper Large or OpenAI Whisper

  • Jojo (VG)

    Where the audio is processed
    On your Mac
    Who can use it
    Anyone with a Mac (macOS 13+)
    Speech model
    Whisper; NB-Whisper can be downloaded

  • transkribere.no

    Where the audio is processed
    Servers in the EU, files deleted within 24 hours
    Who can use it
    Anyone, from NOK 0.49 per minute
    Speech model
    Not stated

  • TurboScribe

    Where the audio is processed
    Cloud
    Who can use it
    Anyone; 3 files of up to 30 minutes a day without paying
    Speech model
    Whisper large-v2

Checked on each service's own website on 11 October 2026. Prices and rules change, so check the service before you decide.

Privacy

The audio and the speech recognition stay on your Mac, and there is no account. Kviskr keeps a copy of each imported file next to the text and deletes both after 30 days unless you change it. Kviskr does not encrypt its history itself, so turn on FileVault. The optional AI modes are off by default. When one is on, the transcribed text, never the audio, is sent to the provider you chose.

What you need

A Mac with Apple silicon (M1 or later) and macOS 15.1 or later. The app takes about 1.3 GB with the standard Norwegian model. Menus and help are in Norwegian, and you are welcome to email hei@kviskr.no in English. For dictation into any app, see Norwegian dictation on Mac.

Frequently asked questions

Transcribe your first Norwegian recording locally.

Free during early access. No account needed. Requires macOS 15.1 or later and Apple silicon.

Or install with Homebrew

Les denne siden på norsk