voice

voice is a command for Claude Code from sonicfieldlabs/akouo. It costs 0 tokens per session (641 once invoked), scanned A, original, MIT.

A command for working with spoken audio and voice-based systems, including transcripts, speech recognition, text-to-speech, voice cloning, and voice agents. It also considers consent, identity, and accessibility.

In plain words
What is it for?
Use it for podcasts, interviews, captions, voice notes, speech-to-text, text-to-speech, dubbing, voice agents, and questions about consent or accessibility.
Why use it?
It separates the sound, words, transcript, generated voice, and identity claims that are often treated as the same thing. This makes voice-related work easier to examine carefully.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

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/sonicfieldlabs/akouo/voice
Clone the repo
git clone --depth 1 https://github.com/sonicfieldlabs/akouo

Made for: Claude Code.

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 voice

README.md
[![agentmods](https://agentmods.dev/badge/commands/sonicfieldlabs/akouo/voice.svg)](https://agentmods.dev/commands/sonicfieldlabs/akouo/voice)
Your own site
<a href="https://agentmods.dev/commands/sonicfieldlabs/akouo/voice"><img src="https://agentmods.dev/badge/commands/sonicfieldlabs/akouo/voice.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 641 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 5.1 $0.00000 $0.00641
Opus 5 $0.00000 $0.00320
Sonnet 5 $0.00000 $0.00128
Haiku 4.5 $0.00000 $0.00064

Measured 6d ago against content hash 0d8a8fd3d5ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

voice 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 6d 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.

commands/voice.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/voice

Purpose

/voice is the voice and speech command. It separates vocal sound, transcript content, ASR output, TTS, voice-agent behavior, identity caution, consent, and access paths.

When To Use

Use /voice for:

  • spoken audio
  • transcripts and captions
  • podcasts, radio, interviews, and voice notes
  • ASR, diarization, TTS, dubbing, voice cloning, and voice agents
  • voice interfaces and agentic workflows
  • identity, consent, intelligibility, or accessibility concerns

Skills Called

  • akouo-router as an implicit planning pass that supplies the evidence inventory, risks, and forbidden assumptions the synthesis must respect
  • voice-speech-listening
  • transductive-media-listening
  • accessibility-normative-listening
  • critical-political-listening when identity, consent, surveillance, platform, dataset, labor, or institutional stakes appear

Execution Order

  1. Run voice-speech-listening to separate vocal sound, speech content, transcript, identity claims, and voice mediation.
  2. Run transductive-media-listening when ASR, TTS, voice agents, voice cloning, codecs, platforms, or model outputs are involved.
  3. Run accessibility-normative-listening to audit captions, transcript path, intelligibility, hearing assumptions, and alternate access.
  4. Run critical-political-listening when the voice is tied to consent, surveillance, labor, dataset, identity, archive, platform, or institutional risk.
  5. Synthesize with strict separation between heard voice, text evidence, model output, interpretation, speculation, and unknowns.

Expected Output

Use schemas/command-output.schema.json.

The output must include:

  • what is voice evidence, transcript evidence, model evidence, or only prompt evidence
  • identity and consent cautions
  • transcript, caption, ASR, or diarization limits
  • access paths and missing access paths
  • mediation chain when known
  • recommended next mode

Guardrails

  • A transcript is not the whole voice.
  • A voice is not proof of identity, age, gender, ethnicity, disability, sincerity, or emotion.
  • ASR and diarization are representations, not neutral capture.
  • Treat consent, dataset provenance, and platform mediation as unknown unless supplied.
  • Keep accessibility integral to voice analysis, not an optional afterthought.

Read the full file on GitHub · 66 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. 6d ago First seen · 66 lines · 0 tokens per session scan A 0d8a8fd3d5ce

Subscribe to this mod's changes

voice is a command published in the GitHub repository sonicfieldlabs/akouo (10 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 641 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 2026-08-31.