happyhorse-1.1-t2v
happyhorse-1.1-t2v is available through TTAPI. Text- and image-to-video generation with clear per-second billing.
Same input, two HappyHorse generations
Grand jeté under spotlights
A professional ballet dancer performs a powerful grand jeté leap across a dimly lit stage, arms outstretched, legs split perfectly in mid-air. The camera follows her in slow motion as she spins into a series of rapid fouettés, tutu flowing dramatically. Spotlights cast long shadows. Cinematic, full-body shot, 10 seconds, ultra HD, dynamic motion blur.
After-school confession
A 15-second cinematic Japanese-style pure romance short, with ultra-realistic image quality. In an empty classroom in the afternoon, warm golden sunlight passes through venetian blinds and falls across adjacent desks. Fine dust drifts slowly through the light beams, and the old wooden desks have realistic texture. The overall scene emphasizes extremely natural micro-movements, breathing, and subtle eye contact. The characters' faces, clothing, and hairstyles remain consistent throughout, with no deformation, drifting, or artifacts. Subtle chest movement syncs with breathing. Shallow depth of field, creamy bokeh background, warm film grain, and sharp 8K image quality create a restrained, breathless atmosphere of youthful Japanese romance. 0-4s: An extremely slow push-in moves from a medium shot of the desks to a side close-up of the two students sitting next to each other. A pure-looking girl in a summer school uniform lowers her head and writes notes carefully. Strands of her long black hair near her ears are gently lifted by a breeze. Her long eyelashes cast delicate shadows; her skin appears naturally soft and rosy. The corners of her mouth lift slightly without intention. She looks focused, breathing softly and evenly. 4-9s: Cut to a close-up of the boy. His school uniform collar is slightly loosened. With one elbow on the desk, he secretly turns his head to gaze at her. His eyes carry tenderness, restraint, affection, and concern. His pupils dilate slightly, and his Adam's apple moves subtly. When he notices her pen pause, he quickly turns away in panic and pretends to look at his own notes. His ears quickly flush light red; his fingertips tremble slightly as he grips his pen. He occasionally steals a glance at her from beneath his bangs. His breathing becomes slightly uneven, and he presses his lips together, trying to stay calm. 9-15s: An extreme close-up of both faces in the same frame. In slow motion, their eyes suddenly meet. The girl first looks dazed and surprised, then quickly lowers her head shyly for 0.3 seconds, gently bites her lower lip, and blushes across her cheeks and ears like cherry blossoms. Her moist eyelashes lift timidly as she looks at him again and whispers shyly, “...What are you looking at?” The boy freezes, pupils widening. After a 0.4-second pause, he stammers quietly in panic, “N-nothing.” The girl bites her lip and steals another glance at him, whispering even more softly, “...Liar.” The boy pauses, then lets out a gentle sigh and says softly, “...Just looking at you.” The corners of his mouth slowly rise into a shy, tender smile, fine lines appearing at the corners of his eyes, and his breathing becomes noticeably heavier. An invisible current of tension seems to pass between their faces; the atmosphere is charged with intimacy as they share the warmth of each other's breath. The background melts into layers of creamy dreamlike bokeh, warm halos, and fine particles in the air. Lip sync is natural and accurate. Emotional tremors, micro-expressions, and breathing are synchronized. Dialogue is delivered as low-energy whispers with shy emotion, with natural short pauses of 200-400 milliseconds. The mouth moves only slightly when speaking, with no exaggeration or robotic quality, creating natural lip sync and authentic emotion. Overall audio: distant summer cicadas are faintly audible; the pen lightly scratches across paper; an almost imperceptible low heartbeat pulse from the two characters; and a very light, airy piano fades in at the end. Dialogue blends naturally into the image as whispered speech. The girl's voice is soft and shy; the boy gradually shifts from flustered stammering to tenderness. The characters maintain consistent identity throughout, with subtle, realistic head tilts, eye movement, and breathing synchronization. No text, watermarks, or subtitles. A clean, emotionally restrained Japanese-style scene of youthful romantic tension.
Kitchen conversation
[Scene] A kitchen at dusk. The range hood hums softly, soup simmers over low heat on the stove, and steam blurs the window glass. [Subjects] The mother stands with her back to the camera, chopping vegetables, her shoulders tense. The daughter sits on a dining chair holding her phone, though her eyes are not on the screen. [Motion] When the daughter begins to speak, the knife in the mother's hand does not stop. When the mother replies, her hand slows for a second. The camera observes from the side in a static shot; the two never make eye contact. [Audio] [Daughter, tentative, like dropping a pebble into water]: “Mom, I want to change jobs.” [The chopping sound pauses for a beat, then continues.] [Mother, voice tightly controlled]: “We'll talk after dinner.” [Silence. The soup bubbles once.] [Daughter, even softer]: “Can you listen to me first?” [The chopping stops. Completely.]
What you can build with happyhorse-1.1-t2v
Prompt driven generation
Submit a concise prompt and get production-ready video output through one TTAPI job.
Core controls only
Keep integration simple with prompt, model, output settings, and callback handling.
Async result flow
Use polling or webhook callbacks so long-running generations do not block your UI.
Ready for product UI
Return HappyHorse results that can be displayed, stored, or passed into downstream workflows.
Per-action, in quota
Usage is metered in quota by model, action, and output settings.
Headers and submit parameters
Use the endpoint below with your TTAPI key and the request fields shown.
/happyhorse/api/v1/services/aigc/video-generation/video-synthesisSubmit a HappyHorse T2V task.
Official reference/happyhorse/api/v1/tasks/{task_id}Retrieve a HappyHorse task result.
Official referenceHeaders
TT-API-KEYstringrequiredYour TTAPI API key.
Content-TypestringrequiredUse application/json.
Body
modelstringrequiredHappyHorse task model such as happyhorse-1.1-t2v.
input.promptstringconditionalText prompt for generation or editing.
input.mediaobject[]conditionalFirst-frame image, reference images, or source video for the selected workflow.
parameters.resolutionenumoptional720P or 1080P output.
parameters.durationintegeroptionalClip duration in seconds.
parameters.ratioenumoptionalOutput aspect ratio for supported workflows.
parameters.watermarkbooleanoptionalWhether to include the HappyHorse watermark.
parameters.seedintegeroptionalRandom seed from 0 to 2147483647.
From key to first result
Copy the resolved endpoint, authentication headers, and request body for this model.
curl --request POST \
--url https://api.ttapi.io/happyhorse/api/v1/services/aigc/video-generation/video-synthesis \
--header 'TT-API-KEY: $TTAPI_KEY' \
--header 'Content-Type: application/json' \
--data '{"model":"happyhorse-1.1-t2v","input":{"prompt":"slow dolly shot through a lantern-lit alley"},"parameters":{"resolution":"720P","duration":5,"watermark":false}}'