By cartesia-ai
Agent Skills for building with Cartesia: speech + transcription APIs (Sonic + Ink) and Line voice agents.
Integrate Cartesia speech APIs (TTS, STT, voices) in application code or coding-agent workflows. Use when the user asks about Cartesia REST/WebSocket APIs, SDKs, API keys, Sonic TTS, Ink STT, voice IDs, access tokens, or embedding voice in an app. For Cartesia Line deployed agents, CLI deploy, and telephony, use the line-voice-agent skill instead.
Build voice agents with the Cartesia Line SDK. Supports 100+ LLM providers via LiteLLM with tool calling, multi-agent handoffs, and real-time interruption handling.
Agent Skills help coding agents ship Cartesia integrations the way we document them: auth, Cartesia-Version, and when to use Line vs raw APIs. Each skill is a versioned SKILL.md (plus optional references/). Contracts live on docs.cartesia.ai; use the Python and JS/TS SDKs in app code and optional MCP in the IDE if you want it.
This repository follows the Agent Skills convention and is also a Claude Code plugin marketplace. Product skills live under skills/cartesia-api/ (HTTP/WebSocket + client libraries) and skills/line-voice-agent/ (Cartesia Line).
npx skills add cartesia-ai/skills
Select cartesia-api and/or line-voice-agent when prompted.
Inside Claude Code, add this repo as a marketplace:
/plugin marketplace add cartesia-ai/skills
Then, install the cartesia-skills plugin:
/plugin install cartesia-skills@cartesia
The plugin vends all skills in this repo.
You can update easily skills using the plugin. First update the cartesia marketplace:
/plugin marketplace update cartesia
Then update the plugin:
```text
/plugin update cartesia-skills
Finally, reload plugins to get the updated skills:
/reload-plugins
| Skill | Path | Use when |
|---|---|---|
| cartesia-api | skills/cartesia-api | Application code: REST/WebSocket, Sonic TTS, Ink STT, voices, SDKs, optional MCP. |
| line-voice-agent | skills/line-voice-agent | Cartesia Line: CLI, cartesia deploy, VoiceAgentApp, telephony, multi-agent tools. |
| Surface | Role |
|---|---|
| This repo | Curated SKILL.md copy and cross-links (docs + OpenAPI stay the contract). |
| docs.cartesia.ai | Full API reference, guides, OpenAPI/AsyncAPI. |
| llms.txt / llms-full.txt | Machine-readable doc indexes for RAG and fetches. |
| SDKs | Python, JS/TS for production integrations. |
| MCP | Optional IDE tooling; not a substitute for SDKs in apps. |
Voice agents on Cartesia Line need a Cartesia key and at least one LLM provider key:
export ANTHROPIC_API_KEY="your-anthropic-key" # or OPENAI_API_KEY, GEMINI_API_KEY, etc.
Cartesia API keys: play.cartesia.ai/keys.
.claude-plugin/
marketplace.json # Claude Code marketplace ("cartesia") vending the plugin
plugin.json # cartesia-skills plugin manifest (plugin root = repo root)
skills/
cartesia-api/ # HTTP/WebSocket, SDKs, optional MCP
line-voice-agent/ # Line SDK, CLI, telephony
Each skill folder has a SKILL.md (whose YAML name matches the folder) and optional references/.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub cartesia-ai/skills --plugin cartesia-skillsUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.