voice-settings

voice-settings is a skill for Claude Code, Codex from michael-L-i/cadence-code. It costs 47 tokens per session (498 once invoked), scanned A, original, MIT.

A settings skill for choosing Cadence Code's local speech and transcription models from the Codex or Antigravity interface. Speech models turn text into audio; transcription models turn spoken audio into text.

In plain words
What is it for?
Use it to view available models, select a text-to-speech model or transcription model, and save the choice. Changing models ends an active Cadence Code session after confirmation.
Why use it?
It lets you change which local models handle speaking and listening without starting a voice conversation.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions Codex; $skill-name invocation.

Part of the cadence-code plugin — 4 skills, 4 commands shipped together

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/michael-l-i/cadence-code/voice-settings
Any agent
npx skills add michael-L-i/cadence-code --skill voice-settings
Clone the repo
git clone --depth 1 https://github.com/michael-L-i/cadence-code

Made for: Claude Code, Codex.

Or install cadence-code, the plugin that ships this one along with the rest of its 4 skills, 4 commands.

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-settings

README.md
[![agentmods](https://agentmods.dev/badge/skills/michael-l-i/cadence-code/voice-settings.svg)](https://agentmods.dev/skills/michael-l-i/cadence-code/voice-settings)
Your own site
<a href="https://agentmods.dev/skills/michael-l-i/cadence-code/voice-settings"><img src="https://agentmods.dev/badge/skills/michael-l-i/cadence-code/voice-settings.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 498 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 $0.00047 $0.00498
Opus 5 $0.00023 $0.00249
Sonnet 5 $0.00009 $0.00100
Haiku 4.5 $0.00005 $0.00050

Measured 5d ago against content hash 914ec70f006b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

voice-settings 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 5d 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.

skills/voice-settings/SKILL.md · 34 lines

What it actually says

Cadence Code Settings

Use mcp__cadence-code__voice_status, mcp__cadence-code__voice_models, mcp__cadence-code__voice_configure, and mcp__cadence-code__voice_stop to change the saved speech-model pair. This workflow is configuration only: do not start a voice conversation or use the microphone. Antigravity may display these as the corresponding tools under the cadence-code MCP server.

  1. Call mcp__cadence-code__voice_status.
  2. If ready is true, explain that a model change ends the current Cadence Code session. Ask for confirmation with the host's structured question UI. If the user confirms, call mcp__cadence-code__voice_stop; otherwise end without changing settings.
  3. Call mcp__cadence-code__voice_models. Present separate TTS and STT single-choice selectors using the host's structured question UI. The structured UI starts on the first listed option, so list current.tts and current.stt first with "(Current)" appended to their labels — or the matching first-run defaults entry when an existing custom model is not in the catalog — then the remaining options lightest to heaviest, appending "(Recommended)" to the defaults entry when it is not the current one. Show every option's tier, download size, and short description.
  4. If the user cancels either selector, end without changing settings. Otherwise call mcp__cadence-code__voice_configure with both chosen IDs.
  5. Confirm the selected labels and say the models download when the next $start-talking or /start-talking conversation starts. Do not call mcp__cadence-code__voice_start, mcp__cadence-code__voice_speak, or mcp__cadence-code__voice_listen here. Explain that unused model weights remain in the Hugging Face cache until the user removes them.
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.

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. 5d ago First seen · 34 lines · 47 tokens per session scan A 914ec70f006b

Subscribe to this mod's changes

voice-settings is a skill published in the GitHub repository michael-L-i/cadence-code (2 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 498 once invoked, about $0.0002 per session on Opus 5. 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.

Related

Other skills, from other repositories

vocello-design

Use this skill to generate well-branded interfaces and assets for Vocello (a local-first, Apple-native macOS voice-generation app — formerly QwenVoice). Contains essential design guidelines, colors, type, fonts, assets, and a Mac-app UI kit for prototyping voice-studio interfaces, marketing surfaces, and slides.

PowerBeef/Vocello · 69 tokens

add-new-model

Use this skill when the user wants to add or port a new model architecture to MLX-VLM — mapping a Hugging Face modeltype to a new file under mlxvlm/models, writing the ModelConfig, matching layer/weight names, reusing a similar existing model, adding a test class, and validating the port. Covers vision-language…

Blaizzy/mlx-vlm · 83 tokens

benchmarking

Use this skill when the user wants to benchmark an MLX-VLM change and present the numbers in a PR — fork-vs-main A/B comparisons, isolated-module micro-benchmarks, median-of-N timing with warmup, peak-memory reporting, correctness checks, parameter sweeps, and self-contained reproducible bench scripts to paste into a…

Blaizzy/mlx-vlm · 74 tokens

convert-quantize

Use this skill when the user wants to convert a Hugging Face model to MLX or quantize/dequantize one with mlxvlm.convert, including bits and group size, quant modes (affine, mxfp4, nvfp4, mxfp8), RTN vs AWQ, mixed-bit recipes, dtype casts, calibration (text or multimodal), local vs Hub paths, revisions, uploading to…

Blaizzy/mlx-vlm · 99 tokens

cli-inference

Use this skill when the user wants to run or debug MLX-VLM inference from the command line, including uv run mlxvlm.generate, image/audio/video inputs, local model paths, Hugging Face model IDs, deterministic repro commands, and CLI errors around processors, prompts, model loading, or missing weights.

Blaizzy/mlx-vlm · 67 tokens

contributing

Use this skill when the user wants to contribute to MLX-VLM — opening a PR, where model code/config/tests go, backward-compatible config args, running the test suite, code formatting and the pre-commit hooks (black, clang-format), and PR expectations (tests, review, perf evidence). Use it to set up a change so it…

Blaizzy/mlx-vlm · 76 tokens