Happy Horse 1.1
Alibaba's Happy Horse 1.1 generates 3-15 second videos with native audio straight from a text prompt. Dialogue, music, and sound effects are directed through the same prompt as the visuals, and nine aspect ratios from 9:21 to 21:9 cover everything from vertical stories to ultrawide cinematics at 480p, 720p, or 1080p.
32% less than the priciest provider (6 compared). Same model, same output.
Duration
Length of the generated video in seconds (3-15). Billed per second.
Resolution
Output resolution. 1080p is the model's default; 480p is the budget rung.
Aspect Ratio
Aspect ratio of the generated video.
32% less than the priciest provider (6 compared). Same model, same output.
Your result renders here.
Use Happy Horse 1.1 via the API
Generate with Happy Horse 1.1 from your own code. Async by design: submit a generation, get a run id back instantly, poll until it completes. Billed in credits at the best available provider price — from $0.07 per second, audio included.
1 — Start a generation
curl -X POST https://app.scenetra.com/api/v1/generate/happy-horse-1.1-t2v \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"A golden retriever trots down a wooden pier at golden hour, tail wagging, gulls overhead, handheld follow shot","duration":"5","resolution":"1080p"}'Response (202)
{
"runId": "run_abc123",
"status": "PENDING",
"model": "happy-horse-1.1-t2v",
"estimatedCredits": 639,
"statusUrl": "/api/v1/runs/run_abc123"
}2 — Poll until COMPLETED (every 2-5 seconds)
curl https://app.scenetra.com/api/v1/runs/run_abc123 \
-H "Authorization: Bearer YOUR_API_KEY"Response
{
"runId": "run_abc123",
"status": "COMPLETED",
"progress": { "completed": 1, "total": 1 },
"outputs": [
{ "type": "video", "url": "https://images.scenetra.com/..." }
],
"error": null,
"estimatedCredits": 639
}Request fields
| Field | Type | Description | Default |
|---|---|---|---|
| prompt* | string | Describe the scene, action, camera and style. Audio (dialogue, music, effects) is generated natively and directed through the prompt. | — |
| duration | string | Length of the generated video in seconds (3-15). Billed per second.3 · 4 · 5 · 6 · 7 · 8 · 9 · 10 · 11 · 12 · 13 · 14 · 15 | 5 |
| resolution | string | Output resolution. 1080p is the model's default; 480p is the budget rung.480p · 720p · 1080p | 1080p |
| aspect_ratio | string | Aspect ratio of the generated video.16:9 · 9:16 · 1:1 · 4:3 · 3:4 · 4:5 · 5:4 · 9:21 · 21:9 | 16:9 |
| callbackUrl | string (https URL) | Optional. When the run finishes (completed or failed), we POST the final run status to this URL — same shape as the poll response, plus model, params, and chargedCredits. Best-effort; polling remains the source of truth. | |
Unknown fields are rejected with a helpful 400. Media fields take https URLs. There is no provider parameter — every run is routed to the cheapest capable provider automatically.
Good to know
Billing
Runs bill your account credits at provider cost with 0% markup. The submit response includes the credit estimate; failed generations are refunded automatically. Add ?dryRun=1 to get the estimate without running anything.
Errors
Errors are always { "error": { "code", "message" } } with stable codes: unauthorized, model_not_available, invalid_parameter, insufficient_credits, rate_limited. A failed run is not an HTTP error — poll responses report status: "FAILED" with the reason.
What makes Happy Horse 1.1 different
Native audio, directed by your prompt
Happy Horse 1.1 generates picture and sound together. Dialogue, background music, and sound effects come out of the same prompt as the visuals — write "she whispers 'follow me' over distant thunder" and the model stages both the shot and the soundtrack. There is no separate audio pass and no surcharge: the per-second rate covers everything.
Nine aspect ratios, 9:21 to 21:9
Most video models offer three or four ratios. Happy Horse 1.1 offers nine — 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, and the unusually tall 9:21 and ultrawide 21:9. That means native output for vertical stories, square feeds, classic TV framing, and anamorphic-style cinematics without cropping in post.
Any duration from 3 to 15 seconds
Pick any whole second from 3 to 15. Three-second clips are cheap motion tests — a 3-second 480p draft costs about $0.21 — while 15 seconds is enough for a full beat of action with dialogue. Billing is strictly per second, so an 11-second clip costs exactly 11 seconds, not a rounded-up preset.
Draft at 480p, ship at 1080p
480p costs $0.07 per second, 720p $0.099, and 1080p $0.128. A practical loop on a Scenetra board: iterate your prompt at 480p until the motion and audio land, then flip the resolution select to 1080p for the final render — same node, same wiring, billed at provider cost with 0% markup.
Parameters
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt* | text | Describe the scene, action, camera, and style. Audio — dialogue, music, SFX — is generated natively and directed through this prompt. | — |
| Duration | select | Duration of the video in seconds, any whole second from 3 to 15.3 · 4 · 5 · 6 · 7 · 8 · 9 · 10 · 11 · 12 · 13 · 14 · 15 | 5 |
| Resolution | select | Output resolution. 1080p is the model's default; 480p is the budget rung.480p · 720p · 1080p | 1080p |
| Aspect Ratio | select | Aspect ratio of the generated video, from tall 9:21 to ultrawide 21:9.16:9 · 9:16 · 1:1 · 4:3 · 3:4 · 4:5 · 5:4 · 9:21 · 21:9 | 16:9 |
Pricing
From $0.07 per second, audio included
Pay per generation — only pay for what you use.
480p
$0.07/s
per second
720p
$0.099/s
per second
1080p
$0.128/s
per second
What a video costs
| Duration | 480p | 720p | 1080p |
|---|---|---|---|
| 5 seconds | $0.35 | $0.49 | $0.64 |
| 10 seconds | $0.70 | $0.99 | $1.28 |
Use cases
Social content
- Vertical 9:16 story clips
- Sound-on hooks with dialogue
- Square feed loops
- Trend-format skits
Film & storytelling
- Ultrawide 21:9 establishing shots
- Dialogue scenes with native audio
- Mood pieces with ambience
- 15-second narrative beats
Marketing & ads
- Product teasers with music
- Multi-ratio campaign variants
- Spoken-tagline bumpers
- Cheap 480p concept tests
Music & audio-led
- Music-driven visuals
- SFX-heavy action clips
- Ambient soundscape loops
- Rhythmic montage drafts
Frequently asked questions
What is Happy Horse 1.1?+
Happy Horse 1.1 is Alibaba's text-to-video model with native audio. You write one prompt describing the scene, camera, style, and sound, and it generates a 3-15 second video at 480p, 720p, or 1080p in any of nine aspect ratios — with dialogue, music, and sound effects baked in. On Scenetra it runs as a node in the visual workflow editor.
Does Happy Horse 1.1 generate audio?+
Yes — audio is native, not an add-on. The model generates the soundtrack together with the picture, and you direct it through the same prompt: name the dialogue, the music mood, or the sound effects you want. There is no audio surcharge; the per-second price covers picture and sound.
How much does Happy Horse 1.1 cost?+
$0.07 per second at 480p, $0.099 at 720p, and $0.128 at 1080p, audio included. A 5-second clip is about $0.35 at 480p and $0.64 at 1080p; a 10-second 1080p clip is about $1.28. Scenetra bills every generation at provider cost with 0% markup.
Can I try Happy Horse 1.1 free online?+
Happy Horse 1.1 is a paid model. On Scenetra it's pay-per-generation with no subscription gate: a 3-second 480p test clip costs about $0.21, so iterating stays cheap.
What aspect ratios and durations does Happy Horse 1.1 support?+
Nine aspect ratios — 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21, and 21:9 — and any whole-second duration from 3 to 15 seconds. That range covers vertical stories, square feeds, and ultrawide cinematic framing natively, without cropping afterwards.
How should I prompt Happy Horse 1.1?+
Treat the prompt as a director's brief covering both picture and sound: describe the subject and action, the camera move, the visual style, and then the audio — lines of dialogue in quotes, the music mood, ambient effects. Concrete beats vague: "slow dolly in as rain hits the window, soft piano underneath" outperforms a paragraph of adjectives. Scenetra's board makes 480p iteration cheap until it lands.
What other modes does Happy Horse 1.1 have?+
Three modes run on Scenetra: Text to Video (this page), Image to Video for animating a first-frame image, and Reference to Video, which generates from up to 9 reference images you cite in the prompt as [Image 1], [Image 2], and so on. You can chain them with other models on the same board.
Related models
MiniMax H3
MiniMax H3 is the newest generation of the Hailuo video lineage: 5-15 second clips with native stereo audio — dialogue, music, and sound effects rendered in the same pass as the picture. Generate at 480P or 768P natively, or step up to 2K and 4K upscaled output, in six aspect ratios from cinematic 21:9 to vertical 9:16.
View model →Seedance 2.5
ByteDance's Seedance 2.5 generates cinematic videos up to 30 seconds from text prompts with synchronized audio — voice, sound effects, and background music — built in by default. The newest Seedance generation, with mp4 or high-fidelity mov output for multi-round editing pipelines.
View model →PixVerse v6
PixVerse's flagship video model generates 1-15 second clips from a text prompt with optional synchronized audio, multi-shot sequences, four resolutions from 360p to 1080p, and eight aspect ratios from vertical 9:16 to cinematic 21:9. Starting at $0.02 per second, it is one of the most affordable ways to produce finished AI video.
View model →Kling 3.0 Pro
Kuaishou's flagship video generation model delivering stunning visual fidelity. Kling 3.0 Pro supports text-to-video, image-to-video with start/end frames, element references for character consistency, and native audio generation.
View model →Start creating with Happy Horse 1.1
Use Happy Horse 1.1 alongside 50+ other AI models in Scenetra's visual workflow editor. No setup required.
Get Started