A command-line speech-to-text tool that turns audio recordings into written transcripts using AIMA’s locally managed model. It accepts common formats such as WAV, MP3, M4A, OGG, and FLAC.

Transcribing interviews, meetings, voice notes, and other audio files for later reading or processing.

It removes the need to type out recordings manually or use a separate transcription service. Transcripts can be printed, saved to a file, or returned as JSON.

aima-asr — Skill for Claude Code and Codex by Approaching-AI

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.

Any agent

npx skills add Approaching-AI/AIMA --skill aima-asr

Clone the repo

git clone --depth 1 https://github.com/Approaching-AI/AIMA

Made for: Claude Code, Codex.

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/skills/approaching-ai/aima/aima-asr.svg)](https://agentmods.dev/skills/approaching-ai/aima/aima-asr)

Your own site

<a href="https://agentmods.dev/skills/approaching-ai/aima/aima-asr"><img src="https://agentmods.dev/badge/skills/approaching-ai/aima/aima-asr.svg" alt="Measured on agentmods" height="20"></a>

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 248 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00023	$0.00248
Opus 5	$0.00012	$0.00124
Sonnet 5	$0.00005	$0.00050
Haiku 4.5	$0.00002	$0.00025

Measured 8d ago against content hash 87e2e62147ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

aima-asr 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/transcribe.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

metadata: {"openclaw":{"emoji":"🎙️","requires":{"bins":["curl"]},"always":true}}

internal/openclaw/skills/aima-asr/SKILL.md · 34 lines

What it actually says

AIMA Speech-to-Text

Transcribe audio files using the ASR model currently managed by AIMA/OpenClaw.

Quick start

{baseDir}/scripts/transcribe.sh /path/to/audio.wav

Useful flags

{baseDir}/scripts/transcribe.sh /path/to/audio.wav --out /tmp/transcript.txt
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --json

Output

Prints transcript to stdout by default
With --out, saves to file and prints the path

Notes

Model: auto-detected from ~/.openclaw/openclaw.json (override with AIMA_ASR_MODEL)
Supported formats: wav, mp3, m4a, ogg, flac
Runs on AIMA proxy at http://127.0.0.1:6188/v1

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/transcribe.sh 1.9 KB runs code

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.

8d ago First seen · 34 lines · 23 tokens per session scan A 87e2e62147ef

Subscribe to this mod's changes

aima-asr is a skill published in the GitHub repository Approaching-AI/AIMA (16 stars, last pushed 6d ago), licensed Apache-2.0. It adds 23 tokens to every session and 248 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.

Creative and media Data and AI ai-agents ai-infrastructure edge-ai inference-engine kubernetes

olares-router

Olares models via olares-cli router — Router (the AI gateway) and the Model Console inside a locally installed model application. Configure cloud vendors and their models, manage local LLM / embedding / audio / OCR model applications, edit a local model's card, name models with aliases, groups and default categories…

beclab/Olares · 202 tokens

h3-anime-character-showcase-pv

Create MiniMax H3 anime or graphic-novel character showcase prompts from a character sheet plus an environment reference, with strict reference-role separation, centered 360-degree character rotation, comic-panel world assembly, readable title choreography, and a seamless loop. Use for character introduction PVs…

linkprint/local-ai-movie-workspace · 91 tokens

h3-layered-windsurfing-fashion-mv

Create MiniMax H3 prompts for original adult windsurfing or fashion-sports music-video arcs using separate identity, equipment, and cinematography reference roles. Use for three-part vertical campaigns, music-shaped action peaks, and text-directed climax segments; do not use for unsafe stunts, real brands, named…

linkprint/local-ai-movie-workspace · 85 tokens

h3-asymmetric-speed-duo-choreography

Create MiniMax H3 prompts for two original adult performers whose movement is governed by an explicit asymmetric action-count ratio, usually 3:1. Use for leader-follower dance, fashion movement, training, or character comedy where one subject deliberately imitates late and never catches up; do not use for synchronized…

linkprint/local-ai-movie-workspace · 80 tokens

h3-chibi-live-action-sticker

Create MiniMax H3 prompts that place one flat 2D chibi or sticker-like character inside a photoreal live-action environment with readable mixed-media interaction. Use for cute drawn mascots affecting real food, desks, streets, hands, or props; do not use for fully animated scenes.

linkprint/local-ai-movie-workspace · 69 tokens

h3-creature-motion-replacement

Create MiniMax H3 prompts for replacing a performer with an original creature while preserving a source video's path, timing, camera, prop interactions, and environment, often with a new cinematic lighting treatment. Use for creature stunt doubles, actor-to-animal replacement, or motion-transfer edits; do not use for…

linkprint/local-ai-movie-workspace · 75 tokens

aima-asr