Private beta open
Vault-encrypted BYOK
SDKs shipping today

Ship secure voice AI
without owning the infrastructure

For teams building realtime voice assistants, AI Gate issues ephemeral WebRTC credentials, runs TURN globally, and keeps your OpenAI keys sealed in our vault so you can focus on product experience.

We are in private beta and review every request within 48–72 hours to co-design the roadmap with early adopters.

Free sandbox stays available while we approve paid plans • No credit card required to start

Stage
Private beta
Onboarding a handful of design partners while we finalize the realtime stack.
Free sandbox
Live
100 sessions/month, vault-encrypted BYOK, and the playground are available today.
Paid plans
By approval
Starter ($29/mo) and Growth ($99/mo) unlock once your beta request is accepted.
Latest release
v1.2.0-beta
Deployed Oct 9, 2025 with worker-to-worker fixes and beta application flow.

Early access designed for builders

We are co-building AI Gate with teams shipping realtime voice AI. Join the private beta to influence the roadmap, secure grandfathered pricing, and get white-glove support while we scale.

Early access to paid plans

Starter ($29/mo) and Growth ($99/mo) unlock before public launch with grandfathered pricing.

  • Preview new releases before broader availability
  • Keep beta pricing when we go GA

Direct line to engineering

You talk directly with the team shipping AI Gate to keep your roadmap in sync with ours.

  • Feedback loops over Slack or async updates
  • Co-design infrastructure fit for your use case

Partner-level support

Hands-on onboarding, billing checks, and integration reviews with 24–48 hour response time.

  • Optional pairing sessions during setup
  • Bug reports get prioritized during beta

We approve applications manually to protect capacity and make sure your use case gets the support it needs.

Roadmap at a glance

We publish our plans so you know exactly what is live, what ships next, and how we reach general availability.

NowNext 1–2 weeks
  • Onboard first cohort of beta testers
  • Collect feedback from sandbox usage
  • Ship beta application notifications
Next1–3 months
  • Add historical metrics and usage alerts
  • Improve retry logic and error reporting
  • Extend security audit logging across the stack
Later3–6 months
  • General availability launch
  • Enterprise plan with custom controls
  • Multi-region deployment and API v2 enhancements

Proof we are already executing

Everything here is running today for our sandbox and beta partners—no aspirational screenshots.

Production & staging live

Web frontend and API are deployed on Cloudflare Workers with mirrored staging environments.

Vault-encrypted BYOK

Keys stay encrypted in D1 + KV; worker-to-worker routing keeps traffic off shared infrastructure.

Active releases

v1.2.0-beta landed Oct 9 with worker fixes, beta application flow, and Stripe environment parity.

What AI Gate handles for you

The same managed infrastructure we operate every day for our beta partners

No Backend to Deploy

Skip the boilerplate. We manage session lifecycle, WebRTC proxying, and TURN configuration for every connection.

Vault-Encrypted BYOK

Bring your OpenAI keys—our vault keeps them encrypted at rest and never exposes them to shared infrastructure.

Instant Ephemeral Keys

Get temporary credentials in milliseconds. Each session gets isolated, time-limited access.

Developer-First SDKs

TypeScript and Python SDKs with full type safety. 5-minute quickstart to production.

Global Edge Network

Deployed on Cloudflare Workers. Low latency worldwide with automatic scaling.

Production Ready

Battle-tested infrastructure with monitoring, rate limiting, and quota management built-in.

How It Works

Three simple steps to production

1

Create Your Project

Sign up and add your OpenAI API key. It is encrypted in our vault and never leaves our infrastructure.

2

Install the SDK

Add our SDK to your app. TypeScript or Python - takes less than 5 minutes.

3

Start Building

Create sessions, connect via WebRTC, and ship your voice AI app. We handle the rest.

Developer-first API

Integrate in Minutes

Full-featured SDKs for TypeScript and Python. Get type safety, auto-completion, and excellent documentation out of the box.

typescript
import { AIGateClient } from '@ai-gate/sdk';

const client = new AIGateClient({
  projectId: 'your-project-id',
});

// Create a voice session
const session = await client.createSession({
  voice: 'echo',
  instructions: 'You are a helpful assistant',
});

// Connect with WebRTC
const pc = new RTCPeerConnection({
  iceServers: session.turn_credentials.iceServers
});

// Start talking! 🎉
Live Demo
Powered by AI Gate
Session created in 87ms
Credentials minted (expires in 1h)
TURN server configured
WebRTC connection established
Ready in 4 minutes

Built in the open with our early access community

Private beta partners
Working closely with a handful of design partners to shape the product.
Infrastructure transparency
Sharing real usage numbers once the platform moves beyond early access.
Security first
Vault-encrypted BYOK pipelines are verified with every customer rollout.
Honest roadmap
We publish status updates so you always know what is live versus planned.

Your Keys, Your Control

We never see your OpenAI keys or audio data. Everything is encrypted in transit and at rest.
Your security is our top priority.

Vault Encryption

AES-256 encryption at rest for all API keys

Zero-Knowledge

We can't read your keys or access your audio

SOC2 Compliant

Security audit in progress (Q2 2025)

GDPR Ready

EU hosting available on request

Built alongside early adopters

Join the beta, help shape the roadmap, and become one of the first teams we feature here.

Collecting real stories

We are onboarding a focused group of teams and will publish their results once they are live in production.

Transparent roadmap

Every feature—including vault-encrypted BYOK and latency benchmarks—is documented as it ships, not before.

Partner-level support

Design partners get direct access to the engineers building AI Gate for feedback and integration help.

How to reach us during beta

We keep feedback loops short so you never wonder what is happening with your voice stack.

Email support

support@ai-gate.dev • responses within 24–48 hours during beta.

Beta requests

Apply at /beta; we review every request manually to keep capacity in check.

Roadmap updates

We publish CURRENT_STATUS.md after each deploy so you always know what shipped.

View live status

Join the AI Gate beta

Tell us about your voice assistant and we will help you launch without rebuilding infrastructure from scratch.

We review beta requests within 48–72 hours • Free sandbox stays open while we scale paid plans