A command that turns text into spoken audio, with options for voice, speed, emotion, and sound effects.

Reading announcements, explanations, stories, and code walkthroughs aloud with a selected voice or style.

It removes the need to read text yourself when audio output is more useful or accessible.

speak — Skill for Claude Code by mcp-tool-shop-org

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 mcp-tool-shop-org/mcp-voice-soundboard --skill speak

Clone the repo

git clone --depth 1 https://github.com/mcp-tool-shop-org/mcp-voice-soundboard

Made for: Claude Code.

Or install mcp-voice-soundboard, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

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/mcp-tool-shop-org/mcp-voice-soundboard/speak/github.svg)](https://agentmods.dev/skills/mcp-tool-shop-org/mcp-voice-soundboard/speak)

Your own site

<a href="https://agentmods.dev/skills/mcp-tool-shop-org/mcp-voice-soundboard/speak"><img src="https://agentmods.dev/badge/skills/mcp-tool-shop-org/mcp-voice-soundboard/speak/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/mcp-tool-shop-org/mcp-voice-soundboard/speak"><img src="https://agentmods.dev/badge/skills/mcp-tool-shop-org/mcp-voice-soundboard/speak.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 420 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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	$0.00019	$0.00420
Opus 5	$0.00010	$0.00210
Sonnet 5	$0.00004	$0.00084
Haiku 4.5	$0.00002	$0.00042

Measured 12d ago against content hash 8a2b95ced35f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

speak 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 12d 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/speak/SKILL.md · 43 lines

What it actually says

Speak

Speak the following aloud: $ARGUMENTS

Instructions

Parse the user's request to determine:
- Text to synthesize
- Voice or preset (if mentioned — e.g. "in a whisper", "use the narrator")
- Speed (if mentioned — e.g. "slowly", "fast")
- Emotion (if the text has emotional content, wrap in emotion spans)
Choose the right preset or voice:
- Casual/friendly → assistant preset
- Documentary/calm → narrator preset
- Energetic/bold → announcer preset
- Story/expressive → storyteller preset
- Soft/gentle → whisper preset
- Specific voice → use voice ID directly (e.g. am_fenrir, bf_alice)
Add emotion spans if the text contains emotional content:
- [happy]...[/happy] for joy, excitement
- [sad]...[/sad] for sadness, disappointment
- [urgent]...[/urgent] for warnings, deadlines
- [calm]...[/calm] for reassurance
Call voice_speak with the prepared text and options
If SFX are appropriate (notifications, alerts), enable sfx: true and use tags like [ding], [chime]

Tips

Default voice is bm_george (British male, authoritative) — good for general announcements
For code walkthroughs, use narrator at speed 0.9 for clarity
Emotion spans can be nested within dialogue for natural-sounding speech
Use voice_status first if unsure what voices are available

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.

12d ago First seen · 43 lines · 19 tokens per session scan A 8a2b95ced35f

Subscribe to this mod's changes

speak is a skill published in the GitHub repository mcp-tool-shop-org/mcp-voice-soundboard (0 stars, last pushed 5d ago), licensed MIT. It adds 19 tokens to every session and 420 once invoked, about $0.0001 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.

Creative and media ai-agents mcp speech-synthesis text-to-speech tts voice

sag

ElevenLabs text-to-speech with mac-style say UX.

JansenAnalytics/claudex · 16 tokens

ElevenLabs — Living Voice

Use when writing or tuning ElevenLabs speech so it sounds alive, paced, and human; covers text shaping for Eleven Multilingual v2 and Eleven v3, plus API-based voice-setting updates from user feedback.

howdeploy/deploychan_mcp · 49 tokens

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.

daxaur/openpaw · 44 tokens

character-matrix

How to interpret the noisy-coding Character Matrix — the four personality sliders (humor, honesty, brevity, chatty) set on the dashboard and delivered as [CHARACTER] instructions. Use whenever a [CHARACTER] instruction arrives, when speaking through the noisy-coding speak tool, or when the user asks about tuning your…

noisy/noisy-coding · 74 tokens

voice-conversations

How voice conversations work with the noisy-coding plugin — trusting [VOICE] messages, answering aloud with the speak tool, spoken-reply conventions, and troubleshooting. Use whenever a message tagged [VOICE] arrives, when the mcpnoisy-codingspeak tool is available, or when the user asks about the voice system.

noisy/noisy-coding · 72 tokens

voice-ai

Use when voice AI — text-to-speech (ElevenLabs, OpenAI TTS), speech-to-text (Whisper), voice cloning, real-time voice agents. Use when working with voice ai.

oyi77/1ai-skills · 44 tokens