Product Updates

A running record of what we have built, fixed, and shipped. No marketing copy -- just what actually changed.

Jun 2026

Rolling OutJune 2026: Rolling out throughout June

VideoReal-time lip sync, gestures, and gaze tracking on capable devices (testing on mid-to-high-end hardware first).

May 2026

This MonthMay 2026: Always there, on your terms

VideoRequest a 'live' photo and receive a 5-10 second clip with subtle motion.

Apr 2026

ShippedApril 2026: Aria-3.5, episodic memory, multilingual TTS, and video generation at 1080p

VideoDeployed a new GPU inference tier; 1080p output now available at p95 generation time of 22s.

Mar 2026

ShippedMarch 2026: TTS v3 prosody model, video generation quality pass, and memory retrieval improvements

VideoReplaced single-pass generation with a two-stage model: keyframe generation followed by frame interpolation.

Feb 2026

ShippedFebruary 2026: Streaming inference, voice call infrastructure, and video generation v1.1

VideoResolution increased from 512x512 to 1280x720.

Jan 2026

ShippedJanuary 2026: New base model, memory architecture, and image generation engine

VideoFirst production video generation model: lip-synced clips from a text prompt and character seed.

Trust & Safety

Our policies, data practices, and safety commitments.