alibaba/happy-horse/v1.1/text-to-video

Happy Horse 1.1 — Text to Video

Happy Horse 1.1 is Alibaba's top-ranked video model. The text-to-video endpoint generates a complete scene from a prompt alone — no input image needed — with synchronized native audio (ambient sound, effects, and spoken dialogue rendered together with the picture) and multilingual lip-sync that keeps mouth movement matched to speech across dozens of languages.

Highlights

• 1080p / 720p output, 3–15s duration.
• Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4 (plus 21:9, 9:21, 5:4, 4:5).
• Native audio generated with the video — write spoken lines directly in the prompt for talking-head and dialogue scenes.
• Multilingual lip-sync — English, French, Spanish, Turkish, Japanese, and more.

Best for

Cinematic, shot-by-shot sequences (camera moves, shallow depth of field, film grain) and spokesperson / talking-head clips (presenter, anchor, instructor) driven purely by text.