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 mcp-tool-shop-org/mcp-voice-soundboard --skill dialoguegit clone --depth 1 https://github.com/mcp-tool-shop-org/mcp-voice-soundboardWrote 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/mcp-tool-shop-org/mcp-voice-soundboard/dialogue)<a href="https://agentmods.dev/skills/mcp-tool-shop-org/mcp-voice-soundboard/dialogue"><img src="https://agentmods.dev/badge/skills/mcp-tool-shop-org/mcp-voice-soundboard/dialogue/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/mcp-tool-shop-org/mcp-voice-soundboard/dialogue"><img src="https://agentmods.dev/badge/skills/mcp-tool-shop-org/mcp-voice-soundboard/dialogue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00017 | $0.00469 |
| Opus 5.5 | $0.00007 | $0.00188 |
| Sonnet 5.5 | $0.00003 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
dialogue 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 1mo 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.
What it actually says
Dialogue
Create a multi-speaker dialogue: $ARGUMENTS
Instructions
-
Parse the user's request to determine:
- Speakers — who is talking?
- Content — what are they saying?
- Tone — formal, casual, dramatic, educational?
-
Write the script in
Speaker: lineformat:Alice: Welcome everyone! [pause 500ms] Bob: Thanks for the introduction. Alice: [happy]Let's dive in![/happy] -
Choose voice casting based on the speakers:
- Male speakers →
am_*(American) orbm_*(British) - Female speakers →
af_*(American) orbf_*(British) - Match accent to character (e.g. British character →
bf_alice) - Use different voice styles for contrast between speakers
- Male speakers →
-
Call
voice_dialoguewith:script— the formatted dialoguecast— speaker-to-voice mappingconcat: trueif the user wants a single audio file
-
Report what was created: speakers, line count, voices used
Recommended Cast Pairings
| Pairing | Voices | Good For |
|---|---|---|
| Professional duo | af_jessica + bm_george |
Interviews, tutorials |
| Casual friends | am_liam + af_sky |
Conversations, demos |
| Storytelling | bf_emma + bm_fable |
Narratives, audiobooks |
| Debate | am_eric + am_fenrir |
Contrasting viewpoints |
Tips
- Add
[pause 300ms]between speakers for natural pacing - Emotion spans work inside dialogue:
Alice: [surprised]Really?![/surprised] - Use
debug: trueto see the cue sheet and catch parse warnings - Uncast speakers are auto-assigned — but explicit casting sounds better
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.
- 1mo ago First seen · 54 lines · 17 tokens per session scan A 8358f238e76c
dialogue is a skill published in the GitHub repository mcp-tool-shop-org/mcp-voice-soundboard (0 stars, last pushed 7d ago), licensed MIT. It adds 17 tokens to every session and 469 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
sag
ElevenLabs text-to-speech with mac-style say UX.
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.
Speak through a buffered, interruptible agent voice service
Deliver explicitly requested agent speech, or maintain its TTS/playback lifecycle: warm provider connection, early phrase flush, complete-recording playback and confirmed cancellation. Use with an identified service and audio device.
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.
voice
Plant Sprachaufnahme, Transkription und Sprachausgabe mit optionalen, austauschbaren Werkzeugen.
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…