Audio & video transcription

From recording to review-ready transcript.

Turn body camera footage, 911 calls, witness interviews, voicemails, dictation, depositions, and hearings into speaker-labeled, timed text you can review beside the source media.

Built for court reporting and litigation support firms
Planet DeposGallo Legal ServicesFortz Legal ServicesExpress Deposition Services
A certified transcript with speaker labels and timecodes beside the source video and the transcript confidence review panel, above the Create transcript output dialog
100+ languagesAutomatic language handling for multilingual recordings
~8–10 minTypical processing time for a one-hour recording
5 exportsPDF, DOCX, TXT, WebVTT, and SubRip outputs

Processing times are typical rather than guaranteed and vary with recording length, audio quality, speaker count, and system load.

Transcription that stays with the legal work

CaseMark Source keeps the recording, transcription progress, timed transcript, corrections, exports, and approved delivery in one Matter instead of scattering the work across upload links and desktop tools.

A complete audio and video transcription workflow

Common audio and video formats

Upload MP3, M4A, WAV, FLAC, OGG, OPUS, or WebM audio, plus MP4, WebM, MOV, AVI, or MKV video. Source keeps the recording attached to the Matter.

More than 100 languages

Transcribe multilingual recordings with automatic language handling, then keep the original media and resulting text together for review.

Speaker-aware timed text

Separate speakers, retain word-level timing, and format punctuation, numbers, and dates so long recordings are easier to navigate.

Synchronized review

Play the source media beside the transcript, follow the active words, and click testimony to seek the recording.

Search and correction

Find transcript text, move between matches, correct words or speakers, and review uncertain passages against surrounding context.

Five practical exports

Download the reviewed transcript as PDF, DOCX, TXT, WebVTT, or SubRip for legal review, captions, and downstream production.

Typical turnaround

Get to the first review faster than playback.

Transcription typically finishes in a fraction of the recording length, then opens as timed text beside the source media for searching, correction, and export.

1 minute of audio · about 15 seconds10 minutes of audio · about 1–2 minutes1 hour of audio · about 8–10 minutes
A timed transcript open beside synchronized source video in CaseMark Source
CaseMark Source

Transcription is the start of the production loop

Source connects the recording and timed transcript to review, captioned clips, transcript production, Matter intelligence, and controlled client delivery.

Review beside the media

Keep every correction grounded in the source recording.

Create captioned clips

Move from transcript words to reviewed MP4 testimony clips.

Build downstream work

Use the transcript for summaries, Interrogate, and other approved workflows.

Deliver under your brand

Make finished files available through a controlled client portal.

Audio and video transcription use cases

Move recordings into reviewable, exportable text without disconnecting them from the Matter or the work that follows.

Body-worn camera footage

Turn long field recordings into searchable, timed text while preserving the path back to the source video.

911 and dispatch calls

Separate speakers and follow the sequence of a call with word-level timing and synchronized audio review.

Witness interviews

Create reviewable interview transcripts that make specific statements and surrounding context easier to find.

Voicemails and recorded calls

Convert short voice messages and recorded conversations into text that can be searched, shared, and reviewed.

Legal dictation

Turn spoken notes, case observations, and drafted language into editable text without manual retyping.

Depositions and hearings

Move recorded proceedings into speaker-labeled transcripts, synchronized review, captions, and downstream legal work.

Turn the recording into usable legal text

Start with body camera footage, calls, interviews, voicemails, dictation, or recorded proceedings and move directly into reviewable text.