What is arch-voice-design?

A guide to designing voice agents on the Kore.ai Agent Platform, including speech-to-text, language-model, text-to-speech, and direct speech-to-speech setups. It covers how calls recognise speech, decide when a speaker has finished, and handle interruptions and silence.

Use it to plan voice architecture, build speech-recognition tests, tune silence and interruption handling, review greetings and filler speech, and investigate quiet or disconnected calls.

Voice problems can come from recognition, timing, provider, or connection settings rather than the conversation logic. The guide uses test calls and traces to locate those causes.

arch-voice-design — Skill for Codex by Koredotcom/agents-mcp-tools

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 Koredotcom/agents-mcp-tools --skill arch-voice-design

Clone the repo

git clone --depth 1 https://github.com/Koredotcom/agents-mcp-tools

Made for: Codex.

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/koredotcom/agents-mcp-tools/arch-voice-design/github.svg)](https://agentmods.dev/skills/koredotcom/agents-mcp-tools/arch-voice-design)

Your own site

<a href="https://agentmods.dev/skills/koredotcom/agents-mcp-tools/arch-voice-design"><img src="https://agentmods.dev/badge/skills/koredotcom/agents-mcp-tools/arch-voice-design/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/koredotcom/agents-mcp-tools/arch-voice-design"><img src="https://agentmods.dev/badge/skills/koredotcom/agents-mcp-tools/arch-voice-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,837 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	$0.00109	$0.01837
Opus 5.5	$0.00044	$0.00735
Sonnet 5.5	$0.00022	$0.00367
Haiku 4.5	$0.00011	$0.00184

Measured 1mo ago against content hash 8446e8e5038c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arch-voice-design 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.

skills/arch-voice-design/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Voice design

Voice is its own architecture. The most expensive voice mistakes are decisions deferred until after the functional build: ASR quality, timeouts and realtime ownership. Decide them in week one.

Gather the evidence

Read the project runtime and voice latency profile settings with platform_config (get_runtime_config), and the agents' VOICE and EXECUTION.voice blocks with platform_package_model (it reads an exported package: pass its path or files).
Sample real or test calls with debug_session_history (filter channel) and read voice events with debug_traces: voice_dead_air, voice_filler_playback and voice_playback_watchdog. For a call that is not live, pass projectId and source: "historical".
Measure silence from the end of the caller's speech, not from the start of the turn.
Runtime traces can miss provider and gateway events (connection closes, provider settings such as temperature). Ask for gateway logs when the trace does not explain a silence.

Week-one decisions

Decision	Do this
ASR quality	Build an ASR test set before the flows: recognition per intent, language confidence, entity values (names, IDs, dates, amounts, addresses) in every language and accent, backchannel ("uh-huh", "okay"), background noise. See references/asr-test-set.md.
Timeouts	Set provider and per-turn listening settings. Yes/no turns end quickly; identifiers need a pause allowance; open answers need more time.
Pipeline vs realtime	Decide from the experience contract and an eval comparison, not a slide.
Realtime ownership	`runtime_guarded` for freeform agents: the model converses and proposes, Runtime validates order, context writes, required values and tool access. `runtime_owned` for payments, regulated changes and irreversible operations.
Latency profile	Start from `customer_service_voice_low_latency_v1` and override only the keys your use case needs.

Read the full file on GitHub · 126 lines

Files

What ships with it

4 files 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.

1mo ago First seen · 126 lines · 109 tokens per session scan A 8446e8e5038c

Subscribe to this mod's changes

arch-voice-design is a skill published in the GitHub repository Koredotcom/agents-mcp-tools (4 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 1,837 once invoked, about $0.0004 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 2026-10-09.

Building agents Debugging

arch-voice-design next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
arch-voice-designKoredotcom/agents-mcp-tools	Skill	4	1mo ago	MIT	A	109	Codex
systematic-debuggingopen-metadata/OpenMetadata	Skill	16k	today	Apache-2.0	A	37	Claude Code
log-error-digestzebbern/claude-code-guide	Skill	4.7k	today	MIT	A	71	Claude Code, Codex
cwv-optimizeradobe/skills	Skill	326	today	Apache-2.0	A	112	Claude Code
ci-fixersipyourdrink-ltd/bernstein	Skill	1.2k	today	Apache-2.0	A	15	Claude Code, Codex
diagnosing-missing-recordingsPostHog/posthog	Skill	41k	today	none	A	76	Claude Code, Codex
triaging-web-analytics-supportPostHog/posthog	Skill	41k	today	none	A	151	Claude Code, Codex