Video · Alibaba
HappyHorse
Alibaba's 2026 model that generates picture and sound together, with lip-sync in seven languages including French. Pick it for talking characters.
Anonymized Moderate costWhat sets it apart
HappyHorse comes from Alibaba's Taotian Future Life Lab, led by a former technical architect of Kling. It generates video and audio in one pass with lip-sync in seven languages, up to 1080p and 15 s.
- Lip-sync in 7 languages
- Up to 9 reference images (1.1)
- Text, image, reference, video edit
Recommended for: a scene where people speak.
Strengths and limits
Where it shines
- Lip-sync in 7 languages, French included
- Ranked first on the Artificial Analysis video arena at launch (April 2026)
- Same price for 1.0 and 1.1
Think twice when
- Mid-range price, not a budget option
- 1080p at most
- 3 to 15 s, native sound
- 720p or 1080p
- Text, image, references and video to video
Use cases
Multilingual spokesperson
A friendly pharmacist at a counter says in French, 'Bonjour, comment puis-je vous aider ?' with a soft smile. 5 seconds.
Lip-sync covers seven languages including French.
Product in context
Using my product photo as reference, show the loudspeaker on a kitchen counter at morning light, camera slowly pushing in. 8 seconds.
Reference mode keeps the product consistent.
Edit an existing clip
Replace the red jacket with a green raincoat in my clip, keep the walking motion.
1.0 offers a video-edit mode.
Against its rivals
- Wan 3.0Wan 3.0 goes to 30 s and takes documents as input.#3 of 22 on Artificial Analysis Image to Video Arena (1,164 Elo)
- Kling V3Kling V3 adds multi-shot, motion control and a 4K tier.#12 of 22 on Artificial Analysis Image to Video Arena (1,055 Elo)
- MiniMax H3 (Hailuo)MiniMax H3 reaches 2K with open weights.#1 of 22 on Artificial Analysis Image to Video Arena (1,195 Elo)
Version history
Each version, dated, with what it changed over the one before.
Hollow points are earlier versions no longer offered in Sub Rosa.
See the numbers
| Version | Released | Elo |
|---|---|---|
| HappyHorse 1.0 | 2026-04-27 | 1,083 |
| HappyHorse 1.1 | 2026-06-28 | 1,104 |
- HappyHorse 1.0
- Video and audio in a single forward pass with lip-sync in 7 languages.
- Text, image, reference and video-edit endpoints at 720p and 1080p.
- HappyHorse 1.1Latest
- Stronger scene coherence, prompt adherence and temporal consistency.
- Reference-based generation with up to 9 images, 3 to 15 s clips.
Benchmarks
How to read these scores: what a benchmark tells you.
Artificial Analysis Image to Video Arena: #4 of 22 models measured in the catalog. The same blind duel, starting from one image: which clip brings it to life better. An Elo rating: higher is preferred more often. 100 points apart means the higher-rated model wins about 64% of duels.
- 1. MiniMax H3 MaxMiniMax H3 (Hailuo)1,195
- 2. MiniMax H3MiniMax H3 (Hailuo)1,181
- 3. Wan 3.0Wan 3.01,164
- 4. HappyHorse 1.1HappyHorse1,104
- 5. Grok Imagine 1.5Grok Imagine video1,098
- 6. HappyHorse 1.0HappyHorse1,083
- 7. Veo 3.1 Full QualityVeo 3 and 3.11,082
- 8. Wan 2.7Wan 2.x1,077
- 9. Grok ImagineGrok Imagine video1,072
- 10. Veo 3.1 FastVeo 3 and 3.11,066
See the numbers
| Model | Elo |
|---|---|
| 1. MiniMax H3 Max | 1,195 |
| 2. MiniMax H3 | 1,181 |
| 3. Wan 3.0 | 1,164 |
| 4. HappyHorse 1.1 | 1,104 |
| 5. Grok Imagine 1.5 | 1,098 |
| 6. HappyHorse 1.0 | 1,083 |
| 7. Veo 3.1 Full Quality | 1,082 |
| 8. Wan 2.7 | 1,077 |
| 9. Grok Imagine | 1,072 |
| 10. Veo 3.1 Fast | 1,066 |
Artificial Analysis Text to Video Arena with audio: #9 of 18 models measured in the catalog. The duel for clips with sound: picture, voices, effects and how well they match. An Elo rating: higher is preferred more often. Only models that make their own sound take part.
- 1. Wan 3.0Wan 3.01,156
- 2. Seedance 2.5Seedance 2.51,142
- 3. MiniMax H3MiniMax H3 (Hailuo)1,138
- 4. MiniMax H3 MaxMiniMax H3 (Hailuo)1,134
- 5. Flux 3FLUX 3 video1,127
- 6. Seedance 2.0Seedance 2.0 and 1.51,119
- 7. Gemini Omni Flash 1.1Gemini Omni Flash1,113
- 8. Grok Imagine 1.5Grok Imagine video1,044
- 9. HappyHorse 1.1HappyHorse1,043
- 10. Wan 2.7Wan 2.x1,029
- 11. HappyHorse 1.0HappyHorse1,025
See the numbers
| Model | Elo |
|---|---|
| 1. Wan 3.0 | 1,156 |
| 2. Seedance 2.5 | 1,142 |
| 3. MiniMax H3 | 1,138 |
| 4. MiniMax H3 Max | 1,134 |
| 5. Flux 3 | 1,127 |
| 6. Seedance 2.0 | 1,119 |
| 7. Gemini Omni Flash 1.1 | 1,113 |
| 8. Grok Imagine 1.5 | 1,044 |
| 9. HappyHorse 1.1 | 1,043 |
| 10. Wan 2.7 | 1,029 |
| 11. HappyHorse 1.0 | 1,025 |
All 7 models in this family
| Model | Use | Privacy | Price |
|---|---|---|---|
HappyHorse 1.0happyhorse-1-0-text-to-video | Text to video | Anonymized | $0.119 per second of video$0.594 a 5 s clip |
HappyHorse 1.0happyhorse-1-0-image-to-video | Image to video | Anonymized | $0.119 per second of video$0.594 a 5 s clip |
HappyHorse 1.0 Referencehappyhorse-1-0-reference-to-video | References to video | Anonymized | $0.119 per second of video$0.594 a 5 s clip |
HappyHorse 1.0 Edithappyhorse-1-0-video-to-video | Text to video | Anonymized | Shown in the app |
HappyHorse 1.1happyhorse-1-1-text-to-video | Text to video | Anonymized | $0.089 per second of video$0.445 a 5 s clip |
HappyHorse 1.1happyhorse-1-1-image-to-video | Image to video | Anonymized | $0.089 per second of video$0.445 a 5 s clip |
HappyHorse 1.1 Referencehappyhorse-1-1-reference-to-video | References to video | Anonymized | $0.0891 per second of video$0.446 a 5 s clip |
Specifications
| Specification | HappyHorse 1.1 | HappyHorse 1.0 |
|---|---|---|
| Released | June 28, 2026 | April 27, 2026 |
| Accepts | text, images | text, images, video |
| Produces | video, audio | video, audio |
| Clip length | 3 to 15 s, with sound | 3 to 15 s, with sound |
| Resolutions | 1080p, 720p | 1080p, 720p |
| Languages | · | 7 lip-sync languages (EN, ZH, YUE, JA, KO, DE, FR) |
| Price | $0.089 per second of video | $0.119 per second of video |
| Privacy | Anonymized | Anonymized |
Prices, context and lengths from the live catalog on October 16, 2026; parameters and licenses from the maker.
Sources
Everything on this page comes from these pages, read on October 16, 2026 or as dated on each score.