ax-audio

ax-audio is a skill for Claude Code, Codex from dosco/aithy. It costs 85 tokens per session (2,667 once invoked), scanned A, a copy of ax-audio, Apache-2.0.

A reference for adding speech input and spoken-audio output to applications built with the @ax-llm/ax TypeScript library.

In plain words
What is it for?
It is for building batch speech-to-text and text-to-speech features, structured programs that return audio, and conversational or real-time audio interactions.
Why use it?
It clarifies when to transcribe recordings, synthesize speech, define audio fields, or configure live conversations. This helps keep audio data in the form each Ax feature expects.

Skill for Claude CodeCodex

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 skills/dosco/aithy/ax-audio
Any agent
npx skills add dosco/aithy --skill ax-audio
Clone the repo
git clone --depth 1 https://github.com/dosco/aithy

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.

agentmods badge for ax-audio

README.md
[![agentmods](https://agentmods.dev/badge/skills/dosco/aithy/ax-audio.svg)](https://agentmods.dev/skills/dosco/aithy/ax-audio)
Your own site
<a href="https://agentmods.dev/skills/dosco/aithy/ax-audio"><img src="https://agentmods.dev/badge/skills/dosco/aithy/ax-audio.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,667 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 $0.00085 $0.02667
Opus 5 $0.00043 $0.01333
Sonnet 5 $0.00017 $0.00533
Haiku 4.5 $0.00009 $0.00267

Measured yesterday against content hash 608b8cd8297d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ax-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 ax-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.

.claude/skills/ax-audio/SKILL.md · 374 lines

How it starts

The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audio I/O Codegen Rules (@ax-llm/ax)

Use this skill for audio in Ax. Pick the smallest audio surface that matches the job:

  • Use ai.transcribe(...) for batch speech-to-text.
  • Use ai.speak(...) for batch text-to-speech.
  • Use speech:audio signature outputs for structured programs that should return synthesized audio artifacts.
  • Use .chat() audio config for conversational or realtime audio turns.

Core Rules

  • Input :audio is an audio input value: { data, format?, mimeType?, sampleRate?, channels? }.
  • Output :audio is a scripted audio artifact. The model returns plain text for that field; Ax synthesizes it after structured output parsing.
  • Output audio JSON schema is model-facing string, not a binary object.
  • Agents transcribe input audio fields before planner/executor/responder stages by default, so agent stages see text instead of base64 audio.
  • Realtime and conversational audio still use .chat() and modelConfig.audio.
  • Batch signature audio artifacts use forward-time speech options, not modelConfig.audio.

Direct Batch APIs

import { ai } from '@ax-llm/ax';

const llm = ai({ name: 'openai', apiKey: process.env.OPENAI_APIKEY! });

const transcript = await llm.transcribe({
  audio: { data: base64Wav, format: 'wav' },
  model: 'gpt-4o-mini-transcribe',
  language: 'en',
  prompt: 'Product support call',
});

const speech = await llm.speak({
  text: transcript.text,
  model: 'gpt-4o-mini-tts',
  voice: 'alloy',
  format: 'mp3',
});

console.log(transcript.text);
console.log(speech.data);
console.log(speech.transcript);

Providers without the requested batch audio capability throw AxMediaNotSupportedError.

Signature Audio Artifacts

import { ai, ax } from '@ax-llm/ax';

const llm = ai({ name: 'openai', apiKey: process.env.OPENAI_APIKEY! });
const say = ax('question:string -> speech:audio, summary:string');

const result = await say.forward(
  llm,
  { question: 'Explain retries in one sentence.' },
  {
    speech: {
      speak: { voice: 'alloy', format: 'mp3' },
      fields: {
        speech: { voice: 'alloy' },
      },
    },
  }
);

console.log(result.summary);
console.log(result.speech.data);
console.log(result.speech.mimeType);
console.log(result.speech.transcript);

Read the full file on GitHub · 374 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 Changed 608b8cd8297d
  2. 5d ago First seen · 374 lines · 85 tokens per session scan A 6820a47913c3

Subscribe to this mod's changes

ax-audio is a skill published in the GitHub repository dosco/aithy (107 stars, last pushed 4d ago), licensed Apache-2.0. It adds 85 tokens to every session and 2,667 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to ax-audio, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

deuz-sdk

Use when building or changing any AI or LLM feature in TypeScript — chatbot, streaming chat UI, agent, tool calling, structured output, embeddings, RAG, agent memory, MCP client, guardrails, image/speech/video generation — or when about to reach for LangChain, LangGraph, LlamaIndex, the Vercel AI SDK (ai, streamText…

Deuz-AI/Deuz-SDK · 112 tokens

migrate-from-ai-sdk

Use when porting an app from the Vercel AI SDK (ai, @ai-sdk/) to @deuz-sdk/core. Triggers include "migrate from the AI SDK", "replace ai with @deuz-sdk/core", "we use streamText/generateText/useChat and want to switch", removing @ai-sdk/openai or @ai-sdk/anthropic, porting a toUIMessageStreamResponse route, converting…

Deuz-AI/Deuz-SDK · 118 tokens

pi

Use when needing a minimal, extensible terminal AI coding agent harness in TypeScript with plugin architecture. Pi: minimalist terminal AI coding agent emphasizing simplicity and composability.

znlgis/opengis-skills · 35 tokens

model-context

MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.

bobmatnyc/claude-mpm-skills · 34 tokens

build-mcp-server

MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.

bobmatnyc/claude-mpm · 36 tokens

vector-search-patterns

Patterns for implementing in-process vector search in Akashic Context — cosine similarity in TypeScript, searchVectorInProcess(), hybrid merge integration. Preload into agents implementing Sprint 1.

tostechbr/memoryClaw · 42 tokens