Yes. ElevenLabs supports generating talking‑avatar videos in Image & Video. You provide a portrait image and an audio track (e.g., from ElevenLabs Text‑to‑Speech) to produce a lip‑synced video. (elevenlabs.io)
Available lip‑sync/avatar models include:
Omnihuman 1.5: lip‑syncs a static image to your speech audio to create a “talking” video. (elevenlabs.io)
Creatify Aurora: drives an avatar (source image) with your audio and optional text guidance, adding natural facial/hand/body motion beyond basic lip‑sync. (elevenlabs.io)
Output is MP4 (H.264/H.265), with upscaling available up to 4K. (elevenlabs.io)
Notes: Image & Video is currently in beta, and video generation requires a paid plan. (elevenlabs.io)
rough hill
wide kiln