Transcription

Skill CaseMark/legal-plugin/transcription

Claude Skills for case.dev — legal AI vaults, OCR, transcription, and search

Install

npx -y skills add CaseMark/legal-plugin --skill transcription

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Transcribes audio and video files through case.dev with speaker diarization. Supports MP3, WAV, M4A, FLAC, OGG, WEBM, MP4 up to 5GB. Use when the user mentions "transcribe", "transcription", "deposition recording", "hearing audio", "speaker labels", or needs to convert audio/video to text.

SKILL.md

3.2 KB, 748 tokens by cl100k_base, as published. Nobody here has run it

case.dev Transcription

Audio and video transcription with speaker diarization, ideal for depositions, hearings, and recorded proceedings. Supports MP3, WAV, M4A, FLAC, OGG, WEBM, and MP4 up to 5GB.

Requires the casedev CLI. See setup skill for installation and auth.

Start a Transcription

The source file must be in a vault:

casedev transcribe run --vault VAULT_ID --object OBJECT_ID --json

The object must be an audio or video file. Non-media files are rejected.

Flags:

--speaker-labels — enable speaker diarization
--speakers-expected N — hint for number of speakers
--language — language code (e.g., en, es)
--format — output format
--auto-highlights — extract key phrases

Uses focused vault if set via casedev focus set --vault.

Check Status

casedev transcribe status TRANSCRIPTION_ID --json

Returns: ID, status, vault, source/result object IDs, audio duration, word count, confidence.

Statuses: queued -> processing -> completed or failed.

Get Result

casedev transcribe result TRANSCRIPTION_ID --json

Returns the transcript text. If the result is stored as a vault object, it fetches the text automatically. Fails if the job is not yet completed.

Watch Until Complete

casedev transcribe watch TRANSCRIPTION_ID --json

Polls until done, then prints the result. Flags:

--interval / -i — poll interval in seconds (default: 3)
--timeout / -t — max wait in seconds (default: 900)

Common Workflow

Transcribe a deposition recording

# 1. Upload to vault
casedev vault object upload ./deposition-2024-01-15.mp3 --vault VAULT_ID --json

# 2. Start transcription with speaker labels
casedev transcribe run --vault VAULT_ID --object OBJECT_ID --speaker-labels --speakers-expected 4 --json

# 3. Watch until complete
casedev transcribe watch TRANSCRIPTION_ID --json

# 4. Or check status + get result separately
casedev transcribe status TRANSCRIPTION_ID --json
casedev transcribe result TRANSCRIPTION_ID --json

Using the job tracker

# Transcription jobs are auto-tracked
casedev jobs list --type transcribe --json
casedev jobs watch JOB_ID --type transcribe --json

Troubleshooting

"Invalid file type for transcribe": Only audio/video MIME types are accepted. Check the object with casedev vault object list --vault VAULT_ID. Upload audio files, not PDFs.

"Invalid object ID for this vault": Run casedev vault object list --vault VAULT_ID to see valid IDs.

"Transcription is not complete yet": Wait for the job to finish. Use casedev transcribe watch or casedev jobs watch.

Transcription failed: Check casedev transcribe status TRANSCRIPTION_ID --json for the error message. Common causes: corrupted file, unsupported codec, file too large.

Long audio (2+ hours): Increase timeout with --timeout 3600. Large files take proportionally longer.

Gives 0 of the 12 instructions most video audio skills give in 748 tokens

Counted across 622 of the 795 authors here whose files we hold, read 2026-08-07

read individual rule files for detailed explanationsin 21 of 622, across 10 files
render final videoin 13 of 622, across 6 files
Use WAV PCM 16kHz mono audio formatin 12 of 622, across 3 files
Use this skill when dealing with Remotion codein 11 of 622, across 4 files
save generated audio to a WAV filein 11 of 622, across 4 files
handle conversion errors gracefullyin 10 of 622, across 6 files
add captions to videos alwaysin 10 of 622, across 4 files
generate music from text descriptions using MusicGenin 9 of 622, across 2 files
do not skip pipeline layersin 9 of 622, across 3 files
do not make one tool do everythingin 9 of 622, across 3 files
use azure document intelligence for complex pdfsin 9 of 622, across 4 files
never ask the user to paste their full API keyin 9 of 622, across 3 files

Said here and by no other author read

store source file in a vault
verify object is an audio or video file
start transcription using casedev transcribe run
use focused vault if one is set
check status using casedev transcribe status
fetch transcript text using casedev transcribe result

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.