transcribe-audio

transcribe-audio is a command for Gemini CLI from bybren-llc/rendertrust. It costs 0 tokens per session (610 once invoked), scanned A, a copy of transcribe-audio, Apache-2.0.

An audio-to-text command that transcribes supported audio files and adds timestamps to the resulting text.

In plain words
What is it for?
Use it for recordings in formats such as MP3, WAV, or FLAC, with plain-text, SRT, or VTT subtitle output.
Why use it?
It removes the need to listen through recordings while typing, and makes spoken content easier to search or turn into subtitles.

Command for Gemini CLI

Written for Gemini CLI: installed under .gemini/.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/bybren-llc/rendertrust/transcribe-audio
Clone the repo
git clone --depth 1 https://github.com/bybren-llc/rendertrust

Made for: Gemini CLI.

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.

agentmods badge for transcribe-audio

README.md
[![agentmods](https://agentmods.dev/badge/commands/bybren-llc/rendertrust/transcribe-audio.svg)](https://agentmods.dev/commands/bybren-llc/rendertrust/transcribe-audio)
Your own site
<a href="https://agentmods.dev/commands/bybren-llc/rendertrust/transcribe-audio"><img src="https://agentmods.dev/badge/commands/bybren-llc/rendertrust/transcribe-audio.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 610 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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.

ModelPer sessionOnce 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

Measured yesterday against content hash 70c490f069fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 yesterday.

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.

Origin

This is a copy

100% identical to transcribe-audio — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.gemini/commands/media/transcribe-audio.toml · 98 lines

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 """

Read the full file on GitHub · 98 lines

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.

  1. yesterday First seen · 98 lines · 0 tokens per session scan A 70c490f069fd

Subscribe to this mod's changes

transcribe-audio is a command published in the GitHub repository bybren-llc/rendertrust (7 stars, last pushed 5mo ago), licensed Apache-2.0. 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. It is 100% identical to transcribe-audio, differing in 0 lines, and is treated as a copy.