Akapulu Labs logo Akapulu Labs Research

Talking Agents Get More Human

Today’s digest spans real-time lip sync and facial animation, stereoscopic digital humans, and speech models that handle turn-taking, interruptions, and paralinguistic cues more naturally. It also includes progress in multilingual TTS and higher-fidelity voice generation.

Talking Agents Get More Human

CFG fidelity-sync tradeoff: full trajectory analysis and 2x2 schedule factorial From Lip Forcing.

Talking Avatars, Lip Sync & Face Animation

Digital Humans & 3D Avatars

SpeechLLMs & Voice Agents

TTS & Voice Synthesis