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, Artificial Intelligence, 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.

🌐 Visit website 📡 Source on GitHub

36.1/100 thin ▬ flat Agent 26/100 agent aware saas Full breakdown ↓
scored 2026-09-08 · rubric v0.20.0

1 APIs

Company Artificial Intelligence Avatars Video Conversational AI Agents Real-Time Personas Voice Y Combinator

Kin Score

Kin Score How this is scored →
scored 2026-09-08 · rubric v0.20.0

Composite quality — 36.1/100 · thin

Contract Quality 11.7 / 23

Developer Ergonomics 11.9 / 18

Access Clarity 1.9 / 18

Operational Transparency 0.3 / 12

Contract Governance 0.5 / 11

Discoverability 6.8 / 9

Create-or-Update Ergonomics 0.0 / 10

Agent readiness — 26/100 · agent aware

Machine-Readable Contract 18 / 18

Agentic Access Contract 10 / 10

Documented Reversibility 0 / 6

MCP Server 0 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 7 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 0 / 6

Agent Skills 5 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/keyframe-labs: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

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.

Open Collections 5

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

API Collection

OPEN COLLECTION

Sessions LLM models API

OPEN COLLECTION

Sessions LLM models Meet bots API

OPEN COLLECTION

LLM models Sessions API

OPEN COLLECTION

Sessions LLM models Voices API

OPEN COLLECTION

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Keyframe Labs Authentication

http · 1 scheme

SECURITY

Keyframe Labs Domain Security

TLSv1.3 · HSTS

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Keyframe Labs Agentic Access

8 operations · 3 acting · 1 human-in-the-loop

8 operations · 3 acting

AGENTIC

Resources

Get Started 4

Portal, sign-up, and the first successful call

DeveloperPortal

GettingStarted

SignUp

Demo

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess

AgenticAccess

LLMsTxt

LLMsTxt

X-MCPServerCandidate

X-MCPServerCandidate

AgentSkill

AgentSkill

Design & Contract 6

Pagination, idempotency, versioning, errors, and events

Components

Conformance

ErrorCatalog

Lifecycle

Conventions

DataModel

Build 3

SDKs, sample code, and the tooling you integrate with

Packages

Packages

SDKs

SDKs

GitHubOrganization

GitHubOrganization

Access & Security 2

Authentication, authorization, and security posture

DomainSecurity

DomainSecurity

Authentication

Authentication

Operate 1

Status, limits, changes, and where to get help

Support

Support

Commercial 1

Pricing, plans, and the legal terms of use

Pricing

Pricing

Company 4

The organization behind the API

Website

Website

Blog

Blog

LinkedIn

Twitter

Twitter

Other 1

Properties that don't map to a standard resource type

Overlay

Overlay

Source (apis.yml)

aid: keyframe-labs
name: Keyframe Labs
description: 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.
url: https://raw.githubusercontent.com/api-evangelist/keyframe-labs/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- y-combinator
x-tier: stub
x-tier-reason: portfolio-lead
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: true
  label: Hosted service · you call their endpoint
  confidence: high
  source:
  - openapi
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source:
  - authentication
  - security
  generated: '2026-09-03'
  method: derived
specificationVersion: '0.23'
created: '2026-07-17'
modified: '2026-07-19'
image: https://platform.keyframelabs.com/og.png
tags:
- Company
- Artificial Intelligence
- Avatars
- Video
- Conversational AI
- Agents
- Real-Time
- Personas
- Voice
- Y Combinator
tags_raw:
- Company
- AI
- Avatars
- Video
- Conversational AI
- Agents
- Real-Time
- Personas
- Voice
- Y Combinator
apis:
- aid: keyframe-labs:keyframe-labs-llm-models-api
  name: Keyframe Labs LLM models API
  description: The LLM models API from Keyframe Labs — 2 operation(s) for llm models.
  humanURL: https://docs.keyframelabs.com/api-reference
  baseURL: https://api.keyframelabs.com/v1
  tags:
  - LLM Models
  tags_raw:
  - LLM models
  properties:
  - type: OpenAPI
    url: openapi/keyframe-labs-llm-models-api-openapi.yml
- aid: keyframe-labs:keyframe-labs-meet-bots-api
  name: Keyframe Labs Meet bots API
  description: The Meet bots API from Keyframe Labs — 3 operation(s) for meet bots.
  humanURL: https://docs.keyframelabs.com/api-reference
  baseURL: https://api.keyframelabs.com/v1
  tags:
  - Meet bots
  properties:
  - type: OpenAPI
    url: openapi/keyframe-labs-meet-bots-api-openapi.yml
- aid: keyframe-labs:keyframe-labs-sessions-api
  name: Keyframe Labs Sessions API
  description: The Sessions API from Keyframe Labs — 1 operation(s) for sessions.
  humanURL: https://docs.keyframelabs.com/api-reference
  baseURL: https://api.keyframelabs.com/v1
  tags:
  - Sessions
  properties:
  - type: OpenAPI
    url: openapi/keyframe-labs-sessions-api-openapi.yml
- aid: keyframe-labs:keyframe-labs-voices-api
  name: Keyframe Labs Voices API
  description: The Voices API from Keyframe Labs — 2 operation(s) for voices.
  humanURL: https://docs.keyframelabs.com/api-reference
  baseURL: https://api.keyframelabs.com/v1
  tags:
  - Voices
  properties:
  - type: OpenAPI
    url: openapi/keyframe-labs-voices-api-openapi.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: AgenticAccess
  url: agentic-access/keyframe-labs-agentic-access.yml
- type: DomainSecurity
  url: security/keyframe-labs-domain-security.yml
- type: Authentication
  url: authentication/keyframe-labs-authentication.yml
- type: LLMsTxt
  url: llms/keyframe-labs-llms.txt
- type: Packages
  url: packages/keyframe-labs-packages.yml
- type: SDKs
  url: packages/keyframe-labs-packages.yml
- type: Components
  url: components/keyframe-labs-components.yml
- type: X-MCPServerCandidate
  url: mcp/keyframe-labs-mcp.yml
  note: 'Renamed from MCPServer 2026-09-03 (roadmap#247): the manifest self-describes as status: candidate — a tool list derived
    from the published API contracts, not an existing server. The scorer already read the manifest and reported mcp_server
    correctly; the MCPServer type was crediting the artifact-type surfaces with a server that does not exist.'
- type: Overlay
  url: overlays/keyframe-labs-sessions-overlay.yaml
- type: Conformance
  url: conformance/keyframe-labs-conformance.yml
- type: ErrorCatalog
  url: errors/keyframe-labs-problem-types.yml
- type: Lifecycle
  url: lifecycle/keyframe-labs-lifecycle.yml
- type: Conventions
  url: conventions/keyframe-labs-conventions.yml
- type: DataModel
  url: data-model/keyframe-labs-data-model.yml
- type: AgentSkill
  url: skills/_index.yml
- type: Website
  url: https://www.keyframelabs.com
- type: DeveloperPortal
  url: https://docs.keyframelabs.com
- type: Documentation
  url: https://docs.keyframelabs.com
- type: APIReference
  url: https://docs.keyframelabs.com/api-reference
- type: GettingStarted
  url: https://docs.keyframelabs.com/guides/getting-started/quickstart-hosted
- type: SignUp
  url: https://platform.keyframelabs.com
- type: Pricing
  url: https://www.keyframelabs.com/pricing
- type: Blog
  url: https://www.keyframelabs.com/blog
- type: GitHubOrganization
  url: https://github.com/keyframelabs
- type: Support
  url: https://discord.gg/Wfce5xHNd5
- type: Demo
  url: https://demo.keyframelabs.com
- type: LinkedIn
  url: https://www.linkedin.com/company/keyframe-labs-inc
- type: Twitter
  url: https://x.com/KeyframeLabs
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/keyframe-labs"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/keyframe-labs/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/keyframe-labs/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.