Tavus Phoenix-4.5 turns a single image into a realtime talking avatar
msg · x · 2026-09-12
Tavus launched Phoenix-4.5, which turns any character — anime, cartoon, or Pixar-style — into a realtime conversational avatar (PAL) from just one image. The avatar stays faithful to the original and can talk, listen, and move in real time. A user demo shows it already working in a live portal.
Related event: Tavus Launches Phoenix-4.5: Real-Time Digital Humans From a Single Image(2 posts)→
More from Multimodal
- Dense instance segmentation via Muse Wonder + SAM 3.1 on Meta's Model API — nikhilaravi · 2026-10-26
- LichtFeld Studio v0.5.4.3 ships community-built SteadySplats, POPSpa and Voxelization — janusch_patas · 2026-10-26
- One prompt to a 2-3 min narrated short: hands-on test of Antigravity video generation — AI_Andrew · 2026-10-26
- Creator makes 10,564-frame animated short entirely with Gemini toolchain — AI_Andrew · 2026-10-26
- FLUX.3 Klein step-distilled to 4-8 steps with CFG baked in — Fit-Structure-6489 · 2026-10-26
- ostris pre-training "Primal VAE": 1-channel latents match modern 8x VAEs via patching — ostrisai · 2026-10-26