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/AIMA

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/github.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/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" 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 5.5	$0.00009	$0.00099
Sonnet 5.5	$0.00005	$0.00050
Haiku 4.5	$0.00002	$0.00025

Measured 2mo ago against content hash 87e2e62147ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

2mo 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 (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 248 once invoked, about $0.0001 per session on Opus 5.5. 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

on-device-verification

Prove a converted or quantized LiteRT model on the actual device via the CompiledModel API - confirm GPU residency, compare device output against the source model, and diagnose device-only failures such as silent CPU fallback, whole-graph compile ceilings, and fp16 range breaks. Use after conversion or quantization…

google-ai-edge/litert-samples · 99 tokens

accuracy-safe-quantization

Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long…

google-ai-edge/litert-samples · 92 tokens

gpu-clean-conversion

Convert a PyTorch or Hugging Face model into a LiteRT model that runs fully on the GPU via the CompiledModel API with verified-correct output, and lay it out as a model recipe. Use when converting a new model, or when a converted model is rejected by the GPU, falls back to CPU, or returns wrong numbers on device.

google-ai-edge/litert-samples · 76 tokens

litert-conversion-workflow

Convert a Hugging Face LLM or vision-language model checkpoint into a .litertlm bundle that runs on the LiteRT-LM runtime with verified quality - classify the architecture against known runtime walls, pick the recipe family (dense, reasoning, hybrid SSM, VLM), export, quantize, gate the result against the source…

google-ai-edge/litert-samples · 132 tokens

litert-runtime

Configures and implements LiteRT (.tflite) on-device inference on Android in Kotlin using the CompiledModel API on CPU and GPU. Use this skill for any Android LiteRT or .tflite task, including Gradle setup, image classification or vision/audio/embedding helpers, TensorBuffer reuse, CPU memory optimization, Bitmap…

google-ai-edge/litert-samples · 150 tokens

aima-asr