agentmods.dev

stt

A command that turns speech from a local audio file or remote audio URL into written text; this process is called transcription.

In plain words
What is it for?
Use it for recordings such as meetings or interviews, with optional formatted output and JSON results for scripts.
Why use it?
It removes the need to type recordings by hand and can accept options such as a language, speaker separation, and key terms.

Command

52 19d ago A scan 0 tokens original MIT
View the source file Moore-developers/grok-cli
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/moore-developers/grok-cli/stt
Clone the repo
git clone --depth 1 https://github.com/Moore-developers/grok-cli
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 648 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00648
Opus 5 $0.00000 $0.00324
Sonnet 5 $0.00000 $0.00130
Haiku 4.5 $0.00000 $0.00065

Measured 2d ago against content hash 97859ef8601f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stt 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 2d 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.

docs/commands/stt.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

grok-cli stt

Purpose

Transcribe a local audio file or remote audio URL into text.

Common Usage

grok-cli stt ./sample.wav

Specify language:

grok-cli stt ./sample.mp3 --language zh

Transcribe remote audio:

grok-cli stt --url https://example.com/sample.wav --language auto

Advanced transcription parameters:

grok-cli stt ./meeting.wav --diarize --keyterm Grok --keyterm xAI --filler-words

Script or skill usage:

grok-cli stt --json --file ./sample.wav

Parameters

  • PATH: positional audio file to transcribe.
  • --file <PATH>: explicit script-friendly file path.
  • --url <URL>: transcribe a remote audio URL; cannot be used together with PATH or --file.
  • --json: use the standard JSON envelope.
  • --auth-file <PATH>: override the OAuth state file path.
  • --model <MODEL>: command-level model override, mainly for compatibility and usage tagging.
  • --language <LANG>: language code, default en.
  • --format <true|false>: whether to request formatted transcription text, default true.
  • --audio-format <FORMAT>: explicitly declare the raw audio format when container metadata is unavailable.
  • --sample-rate <HZ>: raw audio sample rate.
  • --multichannel: treat audio as multichannel.
  • --channels <CHANNELS>: choose channels such as 0,1.
  • --diarize: enable speaker diarization.
  • --keyterm <TERM>: repeatable keyword hint.
  • --filler-words: keep filler words.
  • --timeout <SECONDS>: request timeout, default 120; increase it for large files.

Behavior

  • One of PATH, --file, or --url is required.
  • --url cannot be combined with local file input.
  • Local files must exist, otherwise invalid_args is returned.
  • Multipart requests send file or url and include format, language, audio_format, sample_rate, multichannel, channels, diarize, keyterm, and filler_words as needed.
  • Access token expiry is checked before the request. If needed, the command refreshes first.
  • Responses read text or transcript.
  • If the upstream returns language, duration, words, or channels, --json preserves those structured fields.
  • Successful calls are written to the local usage SQLite database under audio usage.

Read the full file on GitHub · 84 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. 2d ago First seen · 84 lines · 0 tokens per session scan A 97859ef8601f

Subscribe to this mod's changes

stt is a command published in the GitHub repository Moore-developers/grok-cli (52 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 648 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 2026-08-30.

Creative and mediaWriting and docs
Related

Other commands, from other repositories

audition-voices

Generate voice audition samples for a character using Venice TTS.

jordanurbs/venice-video-harness · 0 tokens

status

Show 3d-design team status and recent activity.

MonumentalSystems/Atlas-Agent-Teams · 10 tokens

music-suno-prompt

Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.

frankxai/Starlight-Intelligence-System · 23 tokens

develop-image-prompt.eval

Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.

davistroy/claude-marketplace · 0 tokens

frontend-3d

You are an expert in 3D web development using Three.js, React Three Fiber, WebGL, and WebGPU. You create immersive 3D experiences for the web.

JoasASantos/ClaudeAdvancedPlugins · 0 tokens

diagram-create

Generate a diagram. Pass a prompt describing what to visualize.

jessepike/diagram-forge · 15 tokens