Audio Transcription

Transcribe audio with Norwegian-optimized AI and speaker identification.

How It Works

1

Upload

Upload audio — MP3, WAV, OGG, M4A, FLAC, and more (up to 200 MB).

2

Configure

Choose language and enable speaker diarization.

3

Download

Get your transcript as TXT, SRT, or VTT. Optionally ingest to corpus.

Two Modes. One Tool.

Every tool works for legal professionals and general business alike. Same power, tailored context.

Legal

Deposition Transcription

Transcribe court hearings, depositions, mediations, and client meetings with speaker identification. Norwegian-optimized AI handles legal terminology, speaker overlap, and formal register. Export as text, SRT subtitles, or ingest directly into your legal corpus.

Sample question

Transcribe this 45-minute court hearing with speaker labels

Sample output

Transcription complete · 44:32 · 3 speakers detected
00:00:12 DommerDa erklærer jeg rettsmote for åpnet. Saken gjelder spørsmål om fast bosted etter barneloven § 36.
00:00:28 Advokat ATakk. Vi viser til skriftlig innlegg datert 14. februar, og vil føre vitne til spørsmålet om samværsordningen.
00:01:05 Advokat BVi bestrider ikke at barnet har uttrykt ønske om mer tid med far, men viser til sakkyndigrapporten…
Dommer: 12:34 · 1,240 words Advokat A: 18:45 · 2,180 words Advokat B: 13:13 · 1,520 words

Ideal for

Court hearings Client consultations Depositions Mediation sessions
Any Industry

Meeting Transcription

Transcribe meetings, interviews, presentations, and calls with automatic speaker identification. Supports Norwegian, English, and 6 other languages. Export as text, SRT/VTT subtitles, or ingest directly into your knowledge base.

Sample question

Transcribe this team standup meeting with speaker labels

Sample output

Transcription complete · 12:05 · 3 speakers detected
00:00:04 Speaker AGood morning everyone. Let’s start with yesterday’s progress. Sarah, you’re up first.
00:00:12 Speaker BThanks. I finished the API integration yesterday and started on the test suite. Should have coverage ready by end of day.
00:00:31 Speaker COn my end, the deployment pipeline is green. I’m picking up the dashboard ticket next.
Speaker A: 3:45 · 420 words Speaker B: 4:20 · 510 words Speaker C: 4:00 · 480 words

Ideal for

Team meetings Interviews Webinars Conference talks

Key Features

NB-Whisper: Norwegian-optimized speech-to-text AI model
Speaker diarization — identifies who speaks when
Supports 8 languages: NO, EN, DE, FR, ES, SV, DA, PL
Export as plain text, SRT subtitles, or WebVTT
Auto-ingest transcripts into your RAG knowledge base
Handles up to 200 MB audio files (MP3, WAV, OGG, M4A, FLAC)
Per-speaker statistics: duration, word count
GPU-accelerated processing for fast turnaround

AI That Collaborates With You

This tool doesn't just process your input and return results. It actively works with you:

  • Asks clarifying questions when your request is ambiguous or could be interpreted multiple ways
  • Offers practical advice based on what it finds in your documents
  • Highlights risks and potential issues you might have overlooked
  • Suggests next steps to deepen your analysis or improve your results

Available On

Free Starter Professional Enterprise
See all plans →

Ready to try Audio Transcription?

Start with a free account. No credit card required.