Made with Wavemaker on September 18, 2026, during an internal voice-assets trial. The source voice is an original ElevenLabs-designed narrator (no human recording or real person's voice); an 88-second sample of it was cloned into a saved voice asset (ElevenLabs instant voice clone, provider verification receipt kept), which spoke the new sentence with eleven_multilingual_v2. The presenter is an original fictional portrait from Z-Image Turbo, prompted against celebrity resemblance. MiniMax H3 Ref2VA (int8), 20 steps, 768x768, 124 frames, anchored the portrait and used the padded speech as its audio guide, on one owned H100. Trimmed from 5.17 s to 3.75 s to drop the silent tail, scaled to 1080x1080, -16 LUFS. Review notes are in the source download.

Wavemaker-authored concept example. Source is study material; model weights and third-party tools are not included. Retain their original licenses. Importing source never starts generation.
