Skip to main content
The SLNG API is REST and WebSocket-native, so any HTTP client works. We also ship a CLI, two SDKs, an agent-skills pack, and an n8n node so you don’t have to write that client yourself.

CLI

voiceai runs text-to-speech and speech-to-text from a terminal. Install with curl, Homebrew, or npm.

JavaScript SDK

voiceai-sdk on npm. Typed client for Node, Bun, and Deno.

Python SDK

voiceai-sdk on PyPI. Sync and async clients for Python 3.9+.

Agent skills

slng-ai/skills teaches coding agents how to call the API.

n8n node

n8n-nodes-slng adds SLNG actions and a voice-agent trigger to n8n workflows.

​
Which one should I use?

They all wrap the same API, so you can mix them. Generate sample audio with the CLI, then call the Python SDK from a notebook to transcribe it.

​
SLNG key

Every tool reads its key from an environment variable. Grab one from app.slng.ai and export it before running the examples on the next pages:
The CLI reads VOICEAI_API_KEY. The JS and Python SDKs default to SLNG_API_KEY but accept an explicit apiKey option. Set both to the same value if you plan to use multiple tools side by side.