Type: AI model or model family
Concepts: LLM Evals Mentioned alongside: PersonaPlex Claude Opus 5.5 Gemini 3.1 Flash Live gpt-realtime Grok Voice Recent briefs: 2026-10-12 2026-10-08 2026-09-28
Recent Updates
- 2026-06-10: Multi-Faceted Interactivity Alignment for Full-Duplex Speech Models (cs.CL updates on arXiv.org) · arxiv.org — arXiv · PersonaPlex
- 2026-07-08: How voice-to-voice models work and why cascaded voice stacks are different (Все статьи подряд / Искусственный интеллект / Хабр) · habr.com — Newo.ai ABBYY ElevenLabs David Yan · Whisper · GPT
- 2026-09-15: Causal Counterfactual Filtering Suppresses Spurious Onsets in Full-Duplex Speech LLMs (breakingnewsofficial) · arxiv.org — Kento Nishi PersonaPlex
- 2026-10-12: People Making Conversation: Evaluating How Naturally Speech Models Converse (breakingnewsofficial) · arxiv.org — LLM Evals gpt-realtime Gemini 3.1 Flash Live Grok Voice · PersonaPlex · Claude Opus 5.5
FAQ
What is Moshi?
Moshi appears in the radar stream as a model or model family. This page is a living index of dated mentions and sources — open Recent Updates and Backlinks for context, not a full product brief.
What does this page track?
Dated radar mentions, source links, related concepts, and builder-relevant context for Moshi, collected automatically by GROUNDING.
When was Moshi last mentioned?
Moshi was most recently mentioned in a radar update dated 2026-10-12.
Category: Text / Language Models