AI video model by Alibaba
Happy Horse 1.1 for clips with sound and speech built in
Happy Horse 1.1 is a video model from Alibaba that generates the picture and the audio together, including lip-synced speech in several languages, according to its model page on fal. In Banana Studio it works from text, one photo, or up to three reference photos.
- From 176 credits
- 5-second clips
- Up to 1080p
- No sound switch
What Happy Horse 1.1 is good at
Sound comes with the picture
Audio is generated together with the video rather than added afterwards, so sound and movement stay in step.
Characters who talk
Write the line a character says in quotes and the model animates the lips to match. Its model page lists lip-sync in several languages.
Ready-to-post quality
Choose 720p or 1080p. There is no lower draft tier, so every clip is sized for posting.
Reference photos
Keep up to three people, products or characters consistent with Put your people in a video.
Happy Horse 1.1 prices in credits
| Setting | Credits |
|---|---|
| 720p | 176 |
| 1080p | 232 |
- Prices are per 5-second clip.
- The exact price for your settings is shown on the Create button before you start.
- The 7-day introduction ($1.99, 240 credits) covers 1 clip at the lowest setting, and the Pro plan's 2,200 monthly credits cover about 12 clips.
Plans: $1.99 for a 7-day introduction with 240 credits, then $29.99 a month for 2,200 credits, or $59.97 every 3 months with 2,200 credits each month. The introduction is a paid period, not a free trial. See plans · How credits work
Modes and shapes
| Mode | Photos | Shapes |
|---|---|---|
| Describe a video | None | 16:9, 9:16, 1:1, 4:3, 3:4 |
| Bring a photo to life | 1 | Follows your photo |
| Put your people in a video | Up to 3 | 16:9, 9:16, 1:1, 4:3, 3:4 |
How to create with Happy Horse 1.1
Pick a mode
Describe a video, bring a photo to life, or put your people in a video with up to three photos.
Write action and dialogue
Describe what happens and put any spoken line in quotes, for example: the barista smiles and says "Your usual?"
Choose 720p or 1080p
Pick the quality and create. The clip and its sound appear in History together.
Try a prompt
Who uses Happy Horse 1.1
Skits and ads
A character delivers a line to camera for a product teaser or a short comedy sketch.
Language content
Short spoken phrases for language-learning posts, with lips that match the words.
Storytellers
Animate a portrait so a character speaks a line from your story.
Good to know
- There is no switch to turn sound off for this model in Banana Studio. Mute or replace the audio in an editor if you need a silent clip.
- Two photos, one video (a first and last frame) is not available for Happy Horse 1.1.
- We have not run our own comparison tests on Happy Horse 1.1 yet; the claims above come from its model page.
- Happy Horse 1.1 is made by Alibaba. Banana Studio is an independent app that offers it and is not affiliated with Alibaba.
- Page reviewed October 25, 2026.
Questions about Happy Horse 1.1
Can Happy Horse 1.1 make people talk?
Yes. Put the spoken line in quotes in your prompt. The model generates speech and matching lip movement together with the video; its model page lists lip-sync in several languages.
How many credits does Happy Horse 1.1 use?
Happy Horse 1.1 costs 176 credits at 720p and 232 at 1080p per 5-second clip. There is no sound switch for this model. The 7-day introduction ($1.99, 240 credits) covers 1 clip at the lowest setting, and the Pro plan's 2,200 monthly credits cover about 12 clips. The exact price for your settings is shown on the Create button before you start.
Can I turn the sound off in Happy Horse 1.1?
Not in Banana Studio; Happy Horse 1.1 always generates audio with the clip. Mute or replace it in any video editor if you need silence.
Why is there no 480p option for Happy Horse 1.1?
The model renders at 720p or 1080p only. For cheap drafts at 480p, try the idea on Wan 3.0 or H3 Max first, then switch models for the final.
Can Happy Horse 1.1 use a first and last frame?
No, that mode is not available for this model. Use Kling 3.0, Wan 3.0 or Seedance for clips that move between two frames.
How long can a Happy Horse 1.1 prompt be?
Keep prompts under 2,500 characters; longer ones can fail. A few clear sentences about the action, the setting and the sound usually work best.