rendertrust: Command for Gemini CLI

.gemini/commands/media/extract-dialogue.toml

extract-dialogue is a command for Gemini CLI from bybren-llc/rendertrust. It costs 0 tokens per session (713 once invoked), scanned A, a copy of extract-dialogue, Apache-2.0.

An audio transcription command that separates dialogue by speaker and includes timestamps for each turn.

In plain words
What is it for?
Use it for interviews, meetings, or other multi-speaker recordings to produce speaker-labelled transcripts in a screenplay-like format.
Why use it?
It makes conversations easier to read by showing who said what, while also flagging overlapping speech and non-verbal sounds.

Command for Gemini CLI

Written for Gemini CLI: installed under .gemini/.

This is bybren-llc/rendertrust's own configuration. It tells Gemini CLI how to work on rendertrust itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rendertrust configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bybren-llc/rendertrust. 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/bybren-llc/rendertrust/dev/.gemini/commands/media/extract-dialogue.toml
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 extract-dialogue

README.md
[![agentmods](https://agentmods.dev/badge/commands/bybren-llc/rendertrust/extract-dialogue.svg)](https://agentmods.dev/commands/bybren-llc/rendertrust/extract-dialogue)
Your own site
<a href="https://agentmods.dev/commands/bybren-llc/rendertrust/extract-dialogue"><img src="https://agentmods.dev/badge/commands/bybren-llc/rendertrust/extract-dialogue.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 713 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 $0.00713
Opus 5 $0.00000 $0.00357
Sonnet 5 $0.00000 $0.00143
Haiku 4.5 $0.00000 $0.00071

Measured yesterday against content hash fb6d2fdc4e4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

extract-dialogue 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 extract-dialogue — 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/extract-dialogue.toml · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

description = "Extract dialogue with speaker diarization"

prompt = """

Extract Dialogue Command

Extract dialogue from audio files with speaker diarization using Gemini's multimodal 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. Identify Speakers

Analyze the audio to detect distinct speakers:

  • Estimate the number of unique speakers
  • Assign consistent labels (Speaker 1, Speaker 2, etc.)
  • Note speaker characteristics (pitch, pace, accent) for differentiation
  • Flag overlapping speech segments

3. Transcribe Per Speaker

Transcribe the audio with speaker attribution:

  • Assign each utterance to the identified speaker
  • Include timestamps for each dialogue turn
  • Preserve natural pauses and interruptions
  • Note non-verbal sounds (laughter, applause, silence)

4. Format Output

Screenplay Format:

SPEAKER 1
(00:00:01)
Welcome everyone. Let's get started with the agenda.

SPEAKER 2
(00:00:06)
Thanks. I'd like to begin with the quarterly results.

SPEAKER 1
(00:00:12)
Go ahead.

JSON with Speaker Labels:

{
  "speakers": ["Speaker 1", "Speaker 2"],
  "dialogue": [
    {"speaker": "Speaker 1", "start": 1.0, "end": 5.5, "text": "Welcome everyone. Let's get started with the agenda."},
    {"speaker": "Speaker 2", "start": 6.0, "end": 11.0, "text": "Thanks. I'd like to begin with the quarterly results."},
    {"speaker": "Speaker 1", "start": 12.0, "end": 13.0, "text": "Go ahead."}
  ]
}

Plain Transcript:

Speaker 1 [00:00:01]: Welcome everyone. Let's get started with the agenda.
Speaker 2 [00:00:06]: Thanks. I'd like to begin with the quarterly results.
Speaker 1 [00:00:12]: Go ahead.

Output Options

  • --screenplay - Screenplay-style format (default)
  • --json - JSON with speaker labels and timestamps
  • --transcript - Plain labeled transcript
  • --speakers N - Hint for expected number of speakers

Read the full file on GitHub · 101 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 · 101 lines · 0 tokens per session scan A fb6d2fdc4e4a

Subscribe to this mod's changes

extract-dialogue 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 713 tokens. A static security scan graded it A with 0 findings. It is 100% identical to extract-dialogue, differing in 0 lines, and is treated as a copy.