New · Released June 23, 2026

Happy Horse 1.1 — Alibaba's AI Video Model with Native Audio

Happy Horse 1.1 is Alibaba's new AI video generation model that creates video and audio together in a single pass, with native lip-sync across seven languages. Announced on June 23, 2026, Happy Horse 1.1 sharpens motion, consistency, and prompt adherence over Happy Horse 1.0, and outputs up to 1080p clips of 3 to 15 seconds. Try Happy Horse 1.1 free on SoraVideo.

Try Happy Horse NowView Pricing

Happy Horse 1.1 is available now — generate with it in the tool below.

0/5000

Be specific about motion, scene, and style for the best results

HappyHorse T2V task

5s × 22.5 cr/s

Typical queue time: 8-15 min. You can run up to 3 tasks at once.

If you close this page, you can come back here later or check:
Credits Required: 113|Balance: 0

Enter a prompt to generate a video.

Generate up to 3 videos at once — keep creating while they render.

HappyHorse 1.0 Preview

Text to Video is ready.

Configure the mode-specific inputs and start a task. Results appear here and in recent history.

Recent

Max 20

Sign in to save history

Your generations will sync across all devices

iFree: 1 hour • Pro: 7 days

What is Happy Horse 1.1?

Happy Horse 1.1 is the latest AI video model from Alibaba, built by the Future Life Lab inside Alibaba's Taotian Group and unveiled on June 23, 2026. Happy Horse 1.1 generates video from a text prompt or a starting image, and its standout upgrade is native audio: dialogue, sound effects, ambience, and music are produced together with the motion in a single pass.

Beyond audio, Happy Horse 1.1 adds native lip-sync across seven languages — English, Mandarin, Cantonese, Japanese, Korean, German, and French — with mouth shapes matched to each spoken language. Happy Horse 1.1 outputs 720p or 1080p, in clips of 3 to 15 seconds with a 5-second default, and supports optional first-frame guidance plus up to nine reference images.

Compared with version 1.0, Happy Horse 1.1 delivers upgrades across motion dynamics, subject consistency, prompt adherence, visual quality, and audio. Happy Horse 1.0 ranked #1 on the Artificial Analysis video leaderboard but had very limited public access; Happy Horse 1.1 is available now on SoraVideo, so you can generate with it directly from the tool on this page.

Happy Horse 1.1 generating video and native audio together in a single pass

Key Features of Happy Horse 1.1

What sets Happy Horse 1.1 apart as Alibaba's new audio-and-video AI model

Native Audio Generation

Happy Horse 1.1 generates video and audio together in one pass, so dialogue, sound effects, ambience, and music stay perfectly in sync with the motion — no separate audio step. This native audio is the headline upgrade that sets Happy Horse 1.1 apart from silent video models.

Lip-Sync in 7 Languages

Happy Horse 1.1 provides native lip-sync across English, Mandarin, Cantonese, Japanese, Korean, German, and French, matching mouth shapes to each spoken language. This makes Happy Horse 1.1 a strong fit for multilingual talking-head, dubbing, and character dialogue videos.

1080p Output, Up to 15 Seconds

Happy Horse 1.1 renders 720p or 1080p clips from 3 to 15 seconds, with a 5-second default. Optional first-frame guidance lets you steer how each Happy Horse 1.1 clip begins for tighter creative control.

Up to 9-Image Reference

Happy Horse 1.1 accepts up to nine reference images to lock character identity and visual style. This reference system helps Happy Horse 1.1 keep subjects and scenes consistent across the whole clip.

Sharper Motion & Consistency vs 1.0

Over Happy Horse 1.0, version 1.1 improves motion dynamics, subject consistency, prompt adherence, and overall visual quality. Happy Horse 1.1 is available now in the generator on this page for text-to-video, image-to-video, and reference-to-video.
Happy Horse 1.1 native lip-sync matching mouth motion to speech across languages

How to Generate AI Video with Happy Horse on SoraVideo

Create AI video with Happy Horse 1.1 in four steps on SoraVideo

1

Open the Generator

Open the Happy Horse video generator on this page. Create a SoraVideo account, then purchase credits or choose a plan to use the model.
2

Enter a Prompt or Image

Write a detailed text prompt, or upload a starting image. Describe the scene, characters, motion, and — for the audio-first style Happy Horse 1.1 introduces — the dialogue or sound you want.
3

Choose Your Settings

Select aspect ratio, duration, and resolution. Happy Horse renders up to 1080p and clips up to 15 seconds, matching the runtime range of Happy Horse 1.1.
4

Generate and Download

Generate your video, preview the result, and download it in high quality. Happy Horse 1.1 supports text-to-video, image-to-video, and reference-to-video from the same generator.
Happy Horse 1.1 AI video generation workflow with synchronized audio

Happy Horse 1.1 vs Seedance 2.0 vs Kling 3.0 vs Wan 2.7

How Happy Horse 1.1 compares with leading AI video models including Seedance 2.0, Kling 3.0, and Wan 2.7

FeatureHappy Horse 1.1Seedance 2.0Kling 3.0Wan 2.7
Native Audio✓ + lip-sync———
Lip-Sync Languages7———
Max Resolution1080p1080p1080p1080p
Max Duration15s~15s~10s~10s
Reference ImagesUp to 9MultipleMultipleFew
MakerAlibabaByteDanceKuaishouAlibaba
On SoraVideo✓ Try now✓ FreeOn Kling page—

Comparison based on publicly available specifications as of June 2026. Happy Horse 1.1, Seedance 2.0, Kling 3.0, and Wan 2.7 may change with updates.

Creative Use Cases for Happy Horse 1.1

How Happy Horse 1.1's native audio and multilingual lip-sync open new video workflows

Happy Horse 1.1 use cases — multilingual talking-head and character dialogue video

Multilingual Talking-Head & Dubbing

With lip-sync in seven languages, Happy Horse 1.1 is built for talking-head explainers, dubbing, and localized ads. Creators can produce one script in multiple languages with Happy Horse 1.1 and keep mouth movement natural.

Music & Sound-Driven Shorts

Because Happy Horse 1.1 generates audio with the video, it suits music videos, ASMR, and atmosphere-led shorts where sound and motion must align. This native-audio workflow is what makes Happy Horse 1.1 distinct.

Character Dialogue & Storytelling

Up to nine reference images and synced dialogue let Happy Horse 1.1 hold characters consistent across a scene. Use Happy Horse 1.1 on SoraVideo to build cinematic, character-driven clips today.

Happy Horse 1.1 — Availability & Access

Happy Horse 1.1 was unveiled by Alibaba on June 23, 2026. Here is what is known about Happy Horse 1.1 availability and how to use the Happy Horse model now.

  • Happy Horse 1.1 is made by Alibaba's Taotian Future Life Lab and was announced on June 23, 2026
  • Happy Horse 1.1 generates native audio and provides lip-sync across 7 languages
  • Happy Horse 1.1 outputs 720p/1080p, 3–15 second clips, with first-frame guidance and up to 9 reference images
  • Happy Horse 1.0 ranked #1 on Artificial Analysis benchmarks but had very limited public API and product access
  • Alibaba has not released open weights or a broad public API for Happy Horse; use it through supported platforms
  • Happy Horse 1.1 is available now on SoraVideo for text-to-video, image-to-video, and reference-to-video

For the latest Happy Horse 1.1 features and availability, refer to Alibaba's official announcements.

Learn about Happy Horse

Happy Horse 1.1 FAQ

Common questions about Happy Horse 1.1, Alibaba's new AI video model

Is Happy Horse 1.1 out yet?

Happy Horse 1.1 was unveiled by Alibaba on June 23, 2026, and it is available now on SoraVideo — you can generate with it directly from the tool on this page.

What's new in Happy Horse 1.1 vs 1.0?

Happy Horse 1.1 adds native audio and 7-language lip-sync, and improves motion dynamics, subject consistency, prompt adherence, and visual quality over Happy Horse 1.0.

Can Happy Horse 1.1 really generate audio?

Yes. Happy Horse 1.1 generates video and audio together in a single pass, so dialogue, sound effects, ambience, and music stay in sync with the motion.

Which languages does Happy Horse 1.1 lip-sync?

Happy Horse 1.1 supports native lip-sync in English, Mandarin, Cantonese, Japanese, Korean, German, and French.

How is Happy Horse 1.1 compared with Seedance?

Happy Horse 1.1's edge is native audio and multilingual lip-sync, which Seedance does not focus on. On benchmarks, the Happy Horse family has ranked above Seedance 2.0 for text-to-video quality.

Who makes Happy Horse 1.1?

Happy Horse 1.1 is built by the Future Life Lab inside Alibaba's Taotian Group, announced on June 23, 2026.

Is Happy Horse open source or does it have an API?

Alibaba has not released open weights or a broad public API for Happy Horse. The most reliable way to use it is through supported platforms such as SoraVideo's Happy Horse generator.

Where can I use Happy Horse 1.1 now?

Happy Horse 1.1 is available now on SoraVideo. You can generate with it for text-to-video, image-to-video, and reference-to-video directly from the generator on this page.

Create AI Video with Happy Horse Today

Happy Horse 1.1 brings native audio and multilingual lip-sync from Alibaba. Start generating AI video now with Happy Horse 1.1 on SoraVideo.

Try Happy HorseView Pricing Plans

Happy Horse 1.1 is a product developed by Alibaba. SoraVideo is not affiliated with Alibaba. Information on this page about Happy Horse 1.1 is based on public announcements as of June 2026 and may change. The generator on this page runs Happy Horse 1.1.