Skip to content
Build with AI

Your AI agent, pointed at PyAI.

Give Cursor, Claude Code, Codex, or Lovable one good prompt and the live API contract - and it writes correct PyAI code on the first try. Start free with a sandbox key.

1. Pick what you’re building
2. Tweak the prompt
3. Open your tool

Auto-open where the tool supports it; otherwise copy the command or prompt. Editor tools (Claude Code, Codex) run in your terminal. Or try it live in the Playground →

Cursor

Open a prompt in Cursor and let the agent build.

Open in Cursor
Lovable

Start a new Lovable project from this prompt.

Open in Lovable
Claude Code

Run in your terminal - paste the command.

claude "Help me build with the PyAI voice API (https://api.pyai.com). Before writing code, fetch the machine-readable contract so you never invent endpoints: - OpenAPI spec: https://api.pyai.com/openapi.json - Curated agent index: https://api.pyai.com/llms.txt Use the official SDK where possible: `npm install @pyai/sdk` (TS) or `pip install pyai-sdk` (Python). Auth is a bearer token - I'll paste a sandbox key that looks like pyai_test_... (treat keys as opaque secrets; read from env, never hardcode). PyAI is OpenAI-compatible for /v1/audio/transcriptions and /v1/audio/speech, so you can also point an OpenAI client at base_url https://api.pyai.com/v1. Handle errors by branching on the stable error.code (e.g. 402 credit_exhausted, 429 rate_limit_exceeded). Task: Add streaming text-to-speech to my app: call POST /v1/audio/speech with model \"pyai-voice\" and play the audio progressively from the first byte."
Try it live →
Codex

Run in your terminal - paste the command.

codex "Help me build with the PyAI voice API (https://api.pyai.com). Before writing code, fetch the machine-readable contract so you never invent endpoints: - OpenAPI spec: https://api.pyai.com/openapi.json - Curated agent index: https://api.pyai.com/llms.txt Use the official SDK where possible: `npm install @pyai/sdk` (TS) or `pip install pyai-sdk` (Python). Auth is a bearer token - I'll paste a sandbox key that looks like pyai_test_... (treat keys as opaque secrets; read from env, never hardcode). PyAI is OpenAI-compatible for /v1/audio/transcriptions and /v1/audio/speech, so you can also point an OpenAI client at base_url https://api.pyai.com/v1. Handle errors by branching on the stable error.code (e.g. 402 credit_exhausted, 429 rate_limit_exceeded). Task: Add streaming text-to-speech to my app: call POST /v1/audio/speech with model \"pyai-voice\" and play the audio progressively from the first byte."
Try it live →

What your agent gets

Every prompt points your tool at the same sources of truth, so it never invents an endpoint.

llms.txt

A curated index for AI agents - the fastest way to orient your model.

OpenAPI spec

The machine-readable contract, always in sync with production.

Documentation

Human docs with a try-it console for every endpoint.

Official SDKs

Typed TS (@pyai/sdk) and Python (pyai-sdk) - auth, retries, realtime built in.

Drop the rules into your repo

Want it permanent? Add the PyAI rule or skill so your agent stays correct across every session.

Cursor - project rule

Terminal
cp .cursor/rules/pyai-api.mdc <your-project>/.cursor/rules/

Auto-attaches when you work on PyAI calls.

Claude Code - skill

Terminal
cp -r integrations/claude-skill/pyai-api ~/.claude/skills/

Loads automatically when building against api.pyai.com.

TypeScript SDK

Terminal
npm install @pyai/sdk

Python SDK

Terminal
pip install pyai-sdk

Hand your agent a key and go.

Sign up free, grab a sandbox key, and paste it into your prompt. $50 in free credits, no card.

Build with the API Try the Playground

Agents is live in beta. Sandbox keys have daily limits and never touch billing.