Chert
<p> Vapi for FaceTime: AI video agents in a few lines </p> <p> <a href="https://www.producthunt.com/products/chert?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1223253?app_id=339">Link</a> </p>
Last verified:
What is Chert?
Chert is an AI video agent platform that enables building agents to answer and place FaceTime calls with visual context. Agents can see what callers are showing via camera, making them ideal for remote support, field service, telehealth, and other work requiring visual understanding rather than verbal description alone.
Chert pricing
Pricing model: Freemium
Chert pros
- Vision-enabled agents can access caller's camera context for better problem understanding
- Fully customizable: instructions, model, voice, avatar, framing, and behavior
- Browser-based preview for testing agents before publishing
- Low-code deployment in just a few lines of code
- Multiple use cases: remote support, field service, telehealth intake, visual inspections, customer success
Chert cons
- FaceTime API not generally available yet — currently in controlled private preview only
- Live outbound/inbound calls require explicit provisioning and authorization; accepting mode not enabled by default
- Limited to test workflows until fully launched; not production-ready for all users
Frequently asked questions about Chert
Is the FaceTime API generally available?
Not yet. Chert is onboarding through controlled private preview while production media and line readiness are validated.
Can I test an agent without placing a FaceTime call?
Yes. A browser preview is available for checking prompt, voice, microphone, interruption behavior, avatar, and cleanup before publishing.
Does it support inbound and outbound calls?
The control plane supports bounded inbound and outbound test workflows. Live execution is provisioned and explicitly authorized; accepting mode is not enabled by default.
What can I configure?
Assistant instructions, realtime model, voice, avatar, framing, publishing state, and managed line assignment.