Keyframe Labs

Photoreal conversational avatars with real-time latency for developers

Intermediate API
Screenshot of Keyframe Labs, Photoreal conversational avatars with real-time latency for developers

What is Keyframe Labs?

Keyframe Labs is an avatar tool. Keyframe Labs offers photoreal, real-time conversational avatars driven by its own persona-1.5-live model. Developers pair them with any LLM or voice model through no-code components or a JavaScript SDK, with pricing from $0.06 per minute.

Keyframe Labs builds human foundation models and uses them to power interactive avatars that talk with users in real time. Its first model family includes persona-1.5-live, a 200M parameter model aimed at realistic faces, accurate lip sync, natural motion and a wide range of facial emotion. The result is a video avatar that can sit on top of a voice agent or chatbot and give it a face. The product is aimed at developers and teams that already have a language model or voice stack and want a visual layer for it. Typical uses include customer-facing agents, support, sales and training experiences, and enterprise deployments that need many simultaneous sessions. The company positions the platform for businesses that care about both visual quality and scale, rather than for casual video creation. In practice, setup follows three steps: pick an avatar, connect any LLM or voice model, and go live. The homepage lists compatibility with providers such as OpenAI, ElevenLabs, Cartesia, Gemini, Grok, Hume and Rime, so the avatar acts as a rendering layer rather than a locked-in brain. Teams that want more control can use the JavaScript SDK, which opens an avatar session, receives video and audio tracks for HTML elements, and accepts audio bytes from the team's own model. A LiveKit option is also shown, and docs and example projects are published. An image-to-avatar feature turns a portrait into a usable avatar, and an emotion control system lets builders steer expressions such as happy, skeptical or confused. Performance claims center on a 180ms time-to-first-byte, compared with 450ms or more for other providers according to the vendor's own chart. Enterprise features include thousands of concurrent sessions, multi-region servers in the US, EU and Asia, and a zero data retention mode. Among alternatives, it competes with other real-time avatar and video agent APIs; its distinguishing points are its in-house model research, emotion controls and per-minute pricing starting at $0.06.

How do you use Keyframe Labs?

  1. 1Open the developer platform
    Go to the Keyframe platform and create an account using the Get started button to reach the dashboard for building avatar sessions.
    Keyframe Labs — Open the developer platform
  2. 2Try the live demo
    Start a call in the homepage demo to see the avatar's latency, lip sync and expressions before committing to an integration.
    Keyframe Labs — Try the live demo
  3. 3Select an avatar
    Choose a stock avatar, or upload a portrait to use the image-to-avatar feature and create a custom one.
  4. 4Connect your LLM and voice model
    Pick the language and voice providers you already use, such as OpenAI, ElevenLabs or Cartesia, and link them to the avatar.
  5. 5Integrate with the SDK
    Use the JavaScript SDK to create a client, connect a session, attach the video and audio tracks to page elements and send audio bytes. Docs and examples explain each step.
    Keyframe Labs — Integrate with the SDK
  6. 6Go live and scale
    Launch the session in production, and contact sales if thousands of concurrent sessions, regional servers or zero data retention are needed.

Pros and cons

Pros

  • Claims a 180ms time-to-first-byte, well below the 450ms+ the vendor attributes to other providersAI
  • Works with many LLM and voice providers, including OpenAI, ElevenLabs, Cartesia and GeminiAI
  • Fine-grained emotion control with a broad set of expressions and micro-expressionsAI
  • Image-to-avatar turns a portrait into an avatar, and unlimited call length is advertisedAI
  • Enterprise features: thousands of concurrent sessions, multi-region servers, zero data retention modeAI

Cons

  • Aimed at builders; custom experiences need SDK work, so non-technical users get little hereAI
  • Only one model family is available so far, with more listed as coming soonAI
  • Latency and quality comparisons come from the vendor's own chart and are not independently verifiedAI
  • Per-minute billing can add up for high-volume or always-on deployments, and only an entry price is statedAI

How much does Keyframe Labs cost?

Pricing

Usage-based pricing is advertised from as low as $0.06 per minute. Full plan tiers are not listed on the homepage, and sales contact is offered for larger deployments.

Learn more

Support

Documentation and example projects on GitHub are provided, and a Talk to Sales option books an intro call for enterprise needs.

Learn more

Integrations

Works with LLM and voice providers including OpenAI, Cartesia, Grok, ElevenLabs, Gemini, Fish, Qwen, Sonnet, Hume and Rime. Offers a JavaScript SDK with client, server and LiveKit options.

Learn more

Features

Photoreal avatars with lip sync, natural motion and hair and lighting physics; 180ms time-to-first-byte; broad emotion control; image-to-avatar; support for many LLM and voice providers; JavaScript SDK; unlimited call length; zero data retention mode.

Frequently asked questions about Keyframe Labs

  • How much does Keyframe Labs cost?
    Usage-based pricing is advertised from as low as $0.06 per minute. Full plan tiers are not listed on the homepage, and sales contact is offered for larger deployments.
  • Does Keyframe Labs have an API?
    Yes, Keyframe Labs offers an API.
  • How do you use Keyframe Labs?
    The walkthrough on this page covers 6 steps: 1. Open the developer platform 2. Try the live demo 3. Select an avatar 4. Connect your LLM and voice model 5. Integrate with the SDK 6. Go live and scale.
  • What platforms does Keyframe Labs support?
    Keyframe Labs is available on Web App.
  • What does Keyframe Labs integrate with?
    Works with LLM and voice providers including OpenAI, Cartesia, Grok, ElevenLabs, Gemini, Fish, Qwen, Sonnet, Hume and Rime. Offers a JavaScript SDK with client, server and LiveKit options.
  • What are the limitations of Keyframe Labs?
    Aimed at builders; custom experiences need SDK work, so non-technical users get little here. Only one model family is available so far, with more listed as coming soon. Latency and quality comparisons come from the vendor's own chart and are not independently verified.

Status

StatusActive
Views0
Outbound clicks0
Added10/7/2026

Platforms

Web App

Pricing

Paid