Research, with limits. These attributed findings were checked against search excerpts, not hands-on tests. Identity is linked to a primary reference; aliases and renames may still need resolution. Availability and usefulness are not independently assessed. The observed date is not a launch date.
What the sources describe
What it is
Meta AI Research introduced Muse Realtime Avatar in a blog post dated September 23, 2026, describing it as embodiment technology that turns Muse Realtime Voice into expressive, interactive avatars. Per the source, it brings "any character into a live conversation": a photographic portrait responds with subtle expressions while a full-body illustration gestures and shifts posture as it speaks, and animals and everyday objects become expressive. Source ↗
What it can do
The source states Muse Realtime Avatar brings any image to life in real time with expressive facial, hand, and full-body movement. Its appearance and mannerisms remain coherent frame by frame across conversational turns. A rolling window of recent video latents acts as motion context, and the generation continues for as long as the conversation does. Source ↗
Muse Realtime Voice provides the conversational intelligence and produces speech tokens carrying both what is said and how it is delivered. Muse Realtime Avatar consumes the same stream to generate the matching visual performance, keeping voice, lip motion, and expression synchronized. The blog calls the two a single streaming system connecting intelligence, voice, and embodiment. Source ↗
This is a short discovery note. The available evidence does not yet support a complete practical guide.
Research history
Dated observations, not a claim that the product changed each time. Identical evidence does not create a new entry. Later checks can update the last-checked date.
View this observation
Meta AI Research introduced Muse Realtime Avatar in a blog post dated September 23, 2026, describing it as embodiment technology that turns Muse Realtime Voice into expressive, interactive avatars. Per the source, it brings "any character into a live conversation": a photographic portrait responds with subtle expressions while a full-body illustration gestures and shifts posture as it speaks, and animals and everyday objects become expressive. Source ↗
The source states Muse Realtime Avatar brings any image to life in real time with expressive facial, hand, and full-body movement. Its appearance and mannerisms remain coherent frame by frame across conversational turns. A rolling window of recent video latents acts as motion context, and the generation continues for as long as the conversation does. Source ↗
Muse Realtime Voice provides the conversational intelligence and produces speech tokens carrying both what is said and how it is delivered. Muse Realtime Avatar consumes the same stream to generate the matching visual performance, keeping voice, lip motion, and expression synchronized. The blog calls the two a single streaming system connecting intelligence, voice, and embodiment. Source ↗
How this was found
Initial broad query: Meta new AI agents models features launches site:about.fb.com OR site:ai.meta.com OR site:research.meta.ai announcements and documentation updated since 2026-10-03
Model: deepseek/deepseek-v4.1-flash · Policy: web-exploration-v3. Search excerpts are held privately for seven days; source links, evidence hashes and our reviewed paraphrases remain. Linked pages may change.
Muse Realtime Avatar · Evidence & history · Current