Text-to-Video Generation
Create video from a text description.
Prompt exampleA barista in Tokyo welcomes a customer in Japanese ("いらっしゃいませ"), warm cafe ambience, soft jazz, slow dolly forward.
Happy Horse · Plykit
Turn a text prompt or a reference image into a 3–15 second video with audio, in 720p or 1080p. Check the credit price in the generator before you create.
Audio is part of every Happy Horse 1.0 result, so there is no sound switch. Credits depend on the length and the resolution you pick.
Everything listed here is available in the generator above today.
Describe the action, the camera movement and the sound you want.
Upload a reference image and describe the motion. If the subject speaks, write the line and its language.
Every clip is generated with audio. There is no silent option and no separate price for sound.
Pick any whole-second length from 3 to 15.
Use 720p for quick tests and 1080p for the version you keep. 1080p uses more credits than 720p at the same length.
16:9, 9:16, 1:1, 4:3 and 3:4. Pick one before you generate.
Create videos from text or a reference image with Happy Horse 1.0.
Generate video with audio.
Credits for each length at 720p and 1080p. At the same length, 1080p uses more credits than 720p.
| Duration | 720p | 1080p |
|---|---|---|
| 3s | 40 credits | 80 credits |
| 5s | 60 credits | 120 credits |
| 8s | 96 credits | 192 credits |
| 10s | 120 credits | 240 credits |
| 12s | 144 credits | 288 credits |
| 15s | 180 credits | 360 credits |
Generate your first Happy Horse video in three steps.
Describe the action, camera movement, and sound you want.
Pick 3-15 seconds and 720p or 1080p. Pick aspect ratio for your target platform. We suggest a 5s 720p test first, then re-run at 1080p for the keeper.
Generate the video, then preview and download it.
How Happy Horse 1.0 delivers joint audio-video generation in a single forward pass.
Create video from a text description.
Prompt exampleA barista in Tokyo welcomes a customer in Japanese ("いらっしゃいませ"), warm cafe ambience, soft jazz, slow dolly forward.
Bring a still photo to life with natural motion and synced audio. Drop in any reference image and describe the action + dialogue.
Prompt exampleThe street vendor smiles and says "Hello, my friend!" in English, neon signs flicker, drizzle catches the light.
Generate video with audio.
Prompt exampleA French chef explains a recipe in French ("On commence par le beurre…"), pan sizzles, knife taps cutting board, hand-held camera.
Pick a ratio at generation time. Optimized for the major social platforms — no cropping, no letterbox.
Prompt example9:16 vertical clip — a skateboarder lands a kickflip, ambient street, cheering crowd.
| Version | Status on Plykit | Credits |
|---|---|---|
| Happy Horse 1.0 | Available | 40–360 credits |
Plykit is an independent service that provides access to supported Happy Horse models from Alibaba. Plykit is not affiliated with Alibaba.
It depends on the length and the resolution. The table above lists example lengths at 720p and 1080p, and the generator shows the exact quote before you create.
No. Happy Horse 1.0 generates audio together with the video, so every clip has sound and there is no separate price for it.
Some video models on Plykit add a visible watermark until your account has bought credits. As of 18 October 2026 Happy Horse is not one of them. Check the output conditions of the model you select.
You own the content you generate. The rules for commercial use, including any limits set by the model provider, are in our Terms of Service; read the current version before you publish. Terms of Service
Create videos from text or a reference image with Happy Horse 1.0.