ainewsblitz.com

Breaking

Open-source Parlor v2 runs GPT-Live-style voice and vision fully on-device

  • Open Source
  • Foundation Models
  • AI Agents

An open-source stack called Parlor now offers real-time voice-and-camera conversation on a laptop, aiming at capabilities similar to OpenAI’s GPT-Live without sending audio or video to a cloud model by default. Version 2.0.0, dated 3 August 2026, is labeled a research preview: a near-complete rebuild of a cascade pipeline so that speech, vision, turn-taking, and spoken replies stay local.

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 27,589 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year