build-voice-agent

build-voice-agent is a command for Claude Code from cartesia-ai/skills. It costs 13 tokens per session (288 once invoked), scanned C, original, MIT.

A command that builds an AI voice agent using Cartesia Line, a platform for making voice-based agents.

In plain words
What is it for?
Use it to scaffold agents such as appointment booking or customer support, including a way for the agent to end calls, then learn how to initialize, deploy, and call them.
Why use it?
It provides a defined setup process for turning a description into a voice agent while checking Cartesia's current documentation before writing code.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the cartesia-skills plugin — 2 skills, 1 command, 1 MCP server shipped together

Good fit Use it to scaffold agents such as appointment booking or customer support, including a way for the agent to end calls, then learn how to initialize, deploy, and call them.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/cartesia-ai/skills/build-voice-agent
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.

Clone the repo
git clone --depth 1 https://github.com/cartesia-ai/skills

Made for: Claude Code.

Or install cartesia-skills, the plugin that ships this one along with the rest of its 2 skills, 1 command, 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.

agentmods badge for build-voice-agent

README.md
[![agentmods](https://agentmods.dev/badge/commands/cartesia-ai/skills/build-voice-agent/github.svg)](https://agentmods.dev/commands/cartesia-ai/skills/build-voice-agent)
Your own site
<a href="https://agentmods.dev/commands/cartesia-ai/skills/build-voice-agent"><img src="https://agentmods.dev/badge/commands/cartesia-ai/skills/build-voice-agent/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.

agentmods 80×15 button for build-voice-agent

Your own site · 80×15
<a href="https://agentmods.dev/commands/cartesia-ai/skills/build-voice-agent"><img src="https://agentmods.dev/badge/commands/cartesia-ai/skills/build-voice-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 288 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00013 $0.00288
Opus 5 $0.00006 $0.00144
Sonnet 5 $0.00003 $0.00058
Haiku 4.5 $0.00001 $0.00029

Measured 11d ago against content hash a182fbf97718, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

build-voice-agent scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

4. Use the public CLI (`curl -fsSL https://cartesia.sh | sh`), `cartesia-line`, and `VoiceAgentApp`. Cartesia runs Ink STT and Sonic TTS around the agent.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

4. Use the public CLI (`curl -fsSL https://cartesia.sh | sh`), `cartesia-line`, and `VoiceAgentApp`. Cartesia runs Ink STT and Sonic TTS around the agent.
commands/build-voice-agent.md · 28 lines

What it actually says

Build a Cartesia Line voice agent

Scaffold a production Line agent from the user's description.

The user invoked this command with: $ARGUMENTS

Instructions

  1. Fetch https://docs.cartesia.ai/line/start-building/quickstart.md and https://docs.cartesia.ai/llms.txt before writing code.
  2. Read the cartesia-line skill in this plugin (skills/cartesia-line/SKILL.md) and the references it links.
  3. Do not invent Cartesia-Version, Sonic/Ink model IDs, or CLI flags from memory.
  4. Use the public CLI (curl -fsSL https://cartesia.sh | sh), cartesia-line, and VoiceAgentApp. Cartesia runs Ink STT and Sonic TTS around the agent.
  5. Include end_call (or an equivalent) so the agent can hang up.
  6. Use a fast conversational model (Haiku / Flash / mini class). Put slow reasoning behind background tools.
  7. After scaffolding: how to cartesia init, cartesia deploy, and cartesia call.

Example usage

/build-voice-agent a dentist office that books appointments
/build-voice-agent customer support that can transfer to a human
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. 11d ago First seen · 28 lines · 13 tokens per session scan C a182fbf97718

Subscribe to this mod's changes

build-voice-agent is a command published in the GitHub repository cartesia-ai/skills (5 stars, last pushed 19d ago), licensed MIT. It adds 13 tokens to every session and 288 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.