Borrowing it
Nothing to install: this file belongs to bybren-llc/safe-agentic-workflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bybren-llc/safe-agentic-workflow/main/.gemini/commands/media/transcribe-audio.tomlgit clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflowWrote 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.
[](https://agentmods.dev/commands/bybren-llc/safe-agentic-workflow/transcribe-audio)<a href="https://agentmods.dev/commands/bybren-llc/safe-agentic-workflow/transcribe-audio"><img src="https://agentmods.dev/badge/commands/bybren-llc/safe-agentic-workflow/transcribe-audio.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00610 |
| Opus 5 | $0.00000 | $0.00305 |
| Sonnet 5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
transcribe-audio scanned grade A with 0 findings 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 4d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
2 near-identical copies found in the catalogue:
- transcribe-audio — 100% identical, 0 lines differ
- transcribe-audio — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description = "Transcribe audio files to text with timestamps"
prompt = """
Transcribe Audio Command
Transcribe audio files to text with timestamps using Gemini's multimodal audio capabilities.
Target: {{args}}
Supported Formats
MP3, WAV, AIFF, AAC, OGG, FLAC
Workflow
1. Detect Audio File
Verify the target audio file exists and identify its format:
!{file {{args}} 2>/dev/null || echo "File not found"}
2. Transcribe Audio
Process the audio file through Gemini's multimodal input:
- Detect language automatically (or use specified language)
- Transcribe speech with word-level timestamps
- Identify speaker labels when multiple speakers are present
- Flag low-confidence segments for review
3. Format Output
Generate transcription in the requested format:
Plain Text:
[00:00:01] Welcome to today's session.
[00:00:05] We'll be covering three main topics.
SRT Subtitles:
1
00:00:01,000 --> 00:00:04,500
Welcome to today's session.
2
00:00:05,000 --> 00:00:08,200
We'll be covering three main topics.
VTT Subtitles:
WEBVTT
00:00:01.000 --> 00:00:04.500
Welcome to today's session.
00:00:05.000 --> 00:00:08.200
We'll be covering three main topics.
JSON with Timestamps:
{
"segments": [
{"start": 1.0, "end": 4.5, "text": "Welcome to today's session.", "speaker": "Speaker 1"},
{"start": 5.0, "end": 8.2, "text": "We'll be covering three main topics.", "speaker": "Speaker 1"}
]
}
Output Options
--text- Plain text with timestamps (default)--srt- SRT subtitle format--vtt- WebVTT subtitle format--json- JSON with timestamps and speaker labels
Usage Examples
/media:transcribe-audio ./recording.mp3
/media:transcribe-audio ~/interviews/session1.wav --srt
/media:transcribe-audio ./podcast.aac --json
/media:transcribe-audio ./meeting.ogg --vtt
Notes
- Gemini 3+ required for audio processing
- Audio files up to 100MB supported
- Speaker labels are provided when multiple speakers are detected
- Best results with clear audio and minimal background noise
- Privacy: Audio contents are sent to Gemini API for processing """
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.
- 4d ago First seen · 98 lines · 0 tokens per session scan A 70c490f069fd
transcribe-audio is a command published in the GitHub repository bybren-llc/safe-agentic-workflow (406 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 610 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
record
Start screen/audio recording.
brand-generate
Generate an on-brand document from a saved Brand Profile.
list
List available Piper TTS TTS voices with optional filtering.
init
Initialize project documentation, preferences, or design tokens.
transcribe
Transcribe the file at $ARGUMENTS into Markdown using the Frenchie MCP server.
imperium:create-video
Create startup video content. Supports pitch videos, product demos, social clips, investor updates, and hiring videos. Bridges to Remotion for rendering.