Keyframe Labs
Keyframe Labs builds real-time foundation models that turn AI voice and text agents into lifelike, emotionally expressive video calls. Its Persona-1.5-Live product lets developers add photoreal AI avatars ("personas") to their agents and applications with a few lines of embed code, at roughly 500ms latency and from $0.06 per minute. The platform exposes a REST Sessions API (create a live session, manage meeting bots for Zoom/Meet/Teams, and list voices and LLM models), JavaScript/TypeScript SDKs, and embeddable UI elements, with hosted and self-managed integration paths that plug into agent frameworks such as LiveKit Agents, ElevenLabs Agents, and OpenAI Realtime. Founded in 2025 and backed by Y Combinator (Spring 2026), Keyframe Labs is based in San Francisco.
Keyframe Labs publishes 4 APIs on the APIs.io network, including LLM models API, Meet bots API, Sessions API, and 1 more. Tagged areas include Company, AI, Avatars, Video, and Conversational AI.
Keyframe Labs’ developer surface includes authentication, documentation, API reference, getting-started guide, signup flow, pricing, engineering blog, and 21 more developer resources.
Kin Score
APIs 4
Individual APIs this provider publishes, each with its own machine-readable definition.
Keyframe Labs LLM models API
The LLM models API from Keyframe Labs — 2 operation(s) for llm models.
Keyframe Labs Meet bots API
The Meet bots API from Keyframe Labs — 3 operation(s) for meet bots.
Keyframe Labs Sessions API
The Sessions API from Keyframe Labs — 1 operation(s) for sessions.
Keyframe Labs Voices API
The Voices API from Keyframe Labs — 2 operation(s) for voices.
MCP Servers 1
Model Context Protocol servers that expose these APIs to AI agents.
keyframe-labs-mcp.yml
MCP SERVERSecurity Posture 2
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
Recommended x-agentic-access execution contracts for AI agents.
Resources
Get Started 4
Portal, sign-up, and the first successful call
Documentation 2
Reference material describing how the API behaves
Agent Surfaces 4
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 6
Pagination, idempotency, versioning, errors, and events
Build 3
SDKs, sample code, and the tooling you integrate with
Access & Security 2
Authentication, authorization, and security posture
Operate 1
Status, limits, changes, and where to get help
Commercial 1
Pricing, plans, and the legal terms of use
Company 4
The organization behind the API
Other 1
Properties that don't map to a standard resource type