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.
npx skills add howdeploy/deploychan_mcp --skill elevenlabs-living-voicegit clone --depth 1 https://github.com/howdeploy/deploychan_mcpWrote 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.
[](https://agentmods.dev/skills/howdeploy/deploychan_mcp/elevenlabs-living-voice)<a href="https://agentmods.dev/skills/howdeploy/deploychan_mcp/elevenlabs-living-voice"><img src="https://agentmods.dev/badge/skills/howdeploy/deploychan_mcp/elevenlabs-living-voice/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.
<a href="https://agentmods.dev/skills/howdeploy/deploychan_mcp/elevenlabs-living-voice"><img src="https://agentmods.dev/badge/skills/howdeploy/deploychan_mcp/elevenlabs-living-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 5 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00049 | $0.06776 |
| Opus 5 | $0.00024 | $0.03388 |
| Sonnet 5 | $0.00010 | $0.01355 |
| Haiku 4.5 | $0.00005 | $0.00678 |
Grade A, and why
ElevenLabs — Living 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 674 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ElevenLabs — Living Voice
Overview
This skill is written for any AI agent that generates text for ElevenLabs, including Claude-tyan. You can hand it to an audience as a universal rule for living TTS delivery, not as a local note for one specific setup.
You need it when text for ElevenLabs sounds too flat, plastic, or "just read out loud." Its job is to make speech alive on two layers at once:
- At the text level: rewrite phrases so the model naturally catches pauses, accents, breath, hesitation, and micro-shifts in tempo and intonation.
- At the voice-settings level: use the API voice settings as working knobs to lock in user feedback — speed, stability, similarity, style exaggeration.
The core idea is simple: liveliness isn't born from one magic setting, but from the chain right voice → right model → well-written text → careful feedback loop.
Per the official ElevenLabs docs and help materials:
- Eleven v3 — the most emotional and expressive TTS model layer; well suited for dramatic, warm, characterful delivery.
- Eleven Multilingual v2 — more stable on long chunks and long-form.
- For v3, don't rely on SSML break tags — the docs say plainly that v3 doesn't support them; set pauses and coloring through text, punctuation, and audio tags instead.
- For v2 you can use
<break time="Xs" />; it's the most consistent way to get exact pauses, but overdoing break tags can speed up speech and cause artifacts.
When to Use
Use this skill when:
- you need to turn an ordinary response into living, speakable text;
- the voice sounds too fast, too flat, too theatrical, or too dry;
- the user complains about tempo, liveliness, monotony, lack of emotion, or similarity;
- you need to decide what to fix in the text and what to fix in the API settings;
- you need to lock in a good configuration as the current canonical one.
Don't use it as an excuse to mindlessly clutter the text with special characters. If the speech already sounds natural, don't turn it into a theatrical script with constant [sighs] and an ellipsis every other word.
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.
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.
- 11d ago First seen · 674 lines · 49 tokens per session scan A ec435841cd8c
ElevenLabs — Living Voice is a skill published in the GitHub repository howdeploy/deploychan_mcp (11 stars, last pushed 12d ago), licensed MIT. It adds 49 tokens to every session and 6,776 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 2026-08-30.
Other skills, from other repositories
c-voice
Convert speech to text using sag (ElevenLabs STT) and synthesize speech using say (macOS built-in TTS). Enables voice input transcription and audio output.
talkback
Speak an explanation out loud while working in any project — tiered text-to-speech with a pluggable backend (ElevenLabs by default and quota-guarded, macOS say via --fast for free instant local speech, local OmniVoice as an unlimited private tier). Markdown-aware, so code fences, URLs and deep paths collapse to short…
sag
ElevenLabs text-to-speech with mac-style say UX.
videoagent-audio-studio
Tired of juggling multiple audio APIs? This skill gives you one-command access to TTS, music generation, sound effects, and voice cloning. Use when you want to generate any audio without managing multiple API keys.
voice
Plant Sprachaufnahme, Transkription und Sprachausgabe mit optionalen, austauschbaren Werkzeugen.
dialogue
Create multi-speaker dialogue. Write conversations between characters with different voices.