A command that turns speech in audio or video files into text using the Deepgram API, an online speech-recognition service. It saves the result as a JSON transcript.

Use it with common audio or video files to create punctuated, paragraph-formatted transcripts while retaining filler words such as “um” and “uh”.

It removes the manual work of extracting audio from videos and transcribing recordings with formatting and punctuation.

How jhartquist/claude-remotion-kickstart configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jhartquist/claude-remotion-kickstart. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jhartquist/claude-remotion-kickstart/main/.claude/commands/transcribe.md

Clone the repo

git clone --depth 1 https://github.com/jhartquist/claude-remotion-kickstart

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/jhartquist/claude-remotion-kickstart/transcribe/github.svg)](https://agentmods.dev/commands/jhartquist/claude-remotion-kickstart/transcribe)

Your own site

<a href="https://agentmods.dev/commands/jhartquist/claude-remotion-kickstart/transcribe"><img src="https://agentmods.dev/badge/commands/jhartquist/claude-remotion-kickstart/transcribe/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/jhartquist/claude-remotion-kickstart/transcribe"><img src="https://agentmods.dev/badge/commands/jhartquist/claude-remotion-kickstart/transcribe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 420 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00011	$0.00420
Opus 5	$0.00005	$0.00210
Sonnet 5	$0.00002	$0.00084
Haiku 4.5	$0.00001	$0.00042

Measured 10d ago against content hash cfe0d85f0f39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

transcribe scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Read, Bash(curl*, ffmpeg*)

.claude/commands/transcribe.md · 44 lines

What it actually says

context

The DEEPGRAM_API_KEY environment variable is already set.

For advanced settings (diarization, language detection, etc.), read @context/deepgram.md

task

Transcribe the audio from the media file at $1:

For video files (mp4, mov, avi, mkv, etc.):
- Extract audio to MP3 using ffmpeg: ffmpeg -i input.mp4 -vn -acodec libmp3lame -q:a 2 output.mp3
- Use the original filename stem (e.g., video.mp4 → video.mp3)
- Transcribe the extracted audio file
For audio files (mp3, wav, etc.):
- Transcribe directly
Default transcription settings:
- Use nova-3 model (most accurate)
- Enable smart_format=true for formatting
- Enable punctuate=true for punctuation
- Enable filler_words=true to keep "uh", "um", etc.
- Enable paragraphs=true for structure

API call:

curl -X POST "https://api.deepgram.com/v1/listen?model=nova-3&smart_format=true&punctuate=true&filler_words=true&paragraphs=true" \
  -H "Authorization: Token $DEEPGRAM_API_KEY" \
  -H "Content-Type: audio/mpeg" \
  --data-binary @audio_file.mp3

Save output:
- Save JSON response to {original_filename_stem}_transcript.json
- Example: interview.mp4 → interview_transcript.json
- Report transcript location and show a snippet of the text

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 44 lines · 11 tokens per session scan A cfe0d85f0f39

Subscribe to this mod's changes

transcribe is a command published in the GitHub repository jhartquist/claude-remotion-kickstart (116 stars, last pushed 9mo ago), licensed MIT. It adds 11 tokens to every session and 420 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Creative and media ai claude deepgram elevenlabs nano-banana

claude-remotion-kickstart: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Makes network callslowCapability

What it actually says

context

task

What this file has done since we first saw it

Other commands, from other repositories

video

generate-voiceover

scene-review

design

publish

template