The new Grok Voice 2.0 model is live and will become the default for grok‑voice‑latest on August 5, 2026.
NoteBy OossaPublished by Oossa: 1 min read
xAI announced that Grok Voice 2.0 is now available. The model adds speech‑to‑speech capability, letting users speak to the system and receive spoken replies. From August 5, 2026, the alias grok‑voice‑latest will automatically point to this version. The release notes link to documentation for getting started.
Developers can build voice‑first apps using the new model without updating their endpoint after August 5, 2026.
Models
The new Kandinsky S2V 1.0 Lite (2B) and Pro (21B) models turn speech and a single photo into 25 FPS talking‑head video, and the code is free under MIT.
Models
The new model scores 86.9 on Artificial Analysis' Speech-to-Speech Index, beating OpenAI and Google, and is now live in the Voice Agent API.
Models
YouTube Music will mark tracks that use generative AI with “Fully Gen AI,” “Partly Gen AI,” or “No Gen AI” labels, starting Oct 14 2026.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
