ainewsblitz.com

Breaking

ByteDance Launches SeedRealtime, a Full-Duplex Audio-Video AI Model, in Its Doubao App

ByteDance Launches SeedRealtime, a Full-Duplex Audio-Video AI Model, in Its Doubao App
  • Foundation Models
  • Media Generation

ByteDance on August 5, 2026 launched SeedRealtime, a natively multimodal, full-duplex large language model that lets users talk, watch, and listen with an AI in real time, and made it freely available inside its Doubao consumer app. The company positions the model as a shift from staged, research-grade demos to a mainstream product experience built around continuous audio and video interaction.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year