HeyGen's video and voice models land on fal: built-in sound, 39-language voice cloning
HeyGen · x · 2026-10-22
HeyGen's Video and Voice models are now live on fal. HeyGen Video generates 5-15 second clips at up to 2K from text, images, or reference footage — with dialogue, ambience, and sound effects built into every clip. HeyGen Voice covers 39 languages with instant voice cloning and a faster Turbo tier.
More from Multimodal
- Open-source huashu-motion turns Claude Code into a launch-film studio, 1.3k stars — AlchainHust · 2026-10-22
- Phonon TTS and Fluid Speech Mini: a day-long test of lightweight local speech models — gregbarbosa · 2026-10-22
- AI film studio Shortical plans 20 hours of AI-made vertical micro-dramas a month — lmoroney · 2026-10-22
- Local video generation on 64GB RAM: ComfyUI + LTX-2.5 struggles with character consistency — krustyy · 2026-10-22
- AI music video with authentic 90s rap-VHS vibes, made with MiniMax H3 and Soran't — pwillia7 · 2026-10-22
- Open-source ComfyUI workflow: 4K 600+ frame background replacement with MiniMax H3 tiled diffusion — Emotional_Example_12 · 2026-10-22