curl-X POST 'https://pollo.ai/api/platform/v1/generation/alibaba/happyhorse-1-0/video'\-H'Content-Type: application/json'\-H'x-api-key: YOUR_API_KEY'\-d'{ "input": { "prompt": "A cinematic shot of a golden retriever running through a field of sunflowers at sunset, warm rim light, shallow depth of field", "duration": 5, "resolution": "720p", "aspectRatio": "1:1" }}'
Optionally include webhookUrl to receive a callback when the task succeeds or fails.
Optional request field
{"input":{"prompt":"A cinematic shot of a golden retriever running through a field of sunflowers at sunset, warm rim light, shallow depth of field","duration":5,"resolution":"720p","aspectRatio":"1:1"},"webhookUrl":"https://example.com/webhooks/pollo"}
Schema
Input fields for the selected endpoint and mode.
Field
Type
Required
Description
prompt
string
Yes
Text prompt describing the content to generate.
duration
integer
No
The duration of the generated video, in seconds.
resolution
string
No
Output resolution of the generated media (e.g. 720p, 1080p, 2K, 4K). Values are case-insensitive.
Happy Horse 1.0 generates sound and video together. Spoken lines match mouth movements, ambient audio fits the scene, and camera movements follow the prompt, so clips feel voiced rather than muted.
With Happy Horse 1.0 on Pollo API, developers can add text-to-video and image-to-video generation to their apps, with 720P or 1080P output and clip lengths from 3 to 15 seconds.
Key Features of Happy Horse 1.0 API
Synced Speech and Audio
Keep dialogue, tone, and sound aligned with the visuals, so a talking subject speaks in time instead of drifting out of sync with its own voice.
Accurate Lip-Sync
Keep mouth shapes aligned with spoken words, so speaker-focused shots remain believable when a character delivers a line, counts, or reacts on camera.
Multilingual Delivery
Generate matching spoken output from prompts in different languages, supporting localized versions of the same script without switching tools mid-workflow.
Prompt-Driven Camera Moves
Describe a push-in, pan, or slow orbit and the model stages the motion, giving directed shots instead of a static frame with a talking head.
Fine Length Control
Set clip length from 3 to 15 seconds in one-second steps to match a spoken line, a caption beat, or a loop exactly.
Text and Image Starts
Begin with a written scene or a supplied image, allowing idea-first scripts and asset-first briefs to use the same generation path.
Use Cases of Happy Horse 1.0 API
Talking Avatars: Generate a spokesperson who reads a script aloud with matching lip movement for onboarding flows and virtual presenter tools.
Localized Ad Variants: Produce the same short spot in several languages, each with synced speech, so one campaign ships across regions from one integration.
Explainer Snippets: Turn a written step into a narrated clip where a character speaks the instruction while the camera moves to the detail being described.
Character Voice Lines: Animate a still character image into a short talking shot, giving apps for stories, games, or fan content a speaking figure.
Product Callouts: Have a presenter name a feature and price on camera, with mouth and words aligned, for short shoppable and social placements.
Dubbed Scene Rebuilds: Recreate a scripted moment in a new language with fresh lip-sync, helping localization tools go beyond subtitle overlays.
Social Talking Clips: Fit spoken hooks into 3 to 15 second vertical or square formats for feeds where voiced motion outperforms silent stock.
How to Use Happy Horse 1.0 API
Get an API Key: Create a Pollo API account and generate your API key from the developer dashboard.
Choose the Model: Send requests to the Happy Horse 1.0 endpoint at /generation/wanx/happyhorse-1.0.
Add Your Inputs: Provide a prompt for text-to-video, or an image URL for image-to-video, then set resolution (720P or 1080P) and length (3 to 15). Text-to-video also accepts aspectRatio.
Generate and Retrieve: Submit the task, poll the returned task status, and download the finished video once processing succeeds.
Prompting Best Practices for Happy Horse 1.0 API
Treat the prompt as a script plus a shot list. Write the exact spoken line, name the speaker and language, then describe the camera and setting so audio and motion line up.
A Simple Prompt Formula
Speaker + spoken line in quotes and language + expression or gesture + camera move + setting and audio cue
What You Should Notice
Quote the Dialogue: Put the actual words in the prompt so lip-sync has an exact line to follow rather than a paraphrase.
Name the Language: State the spoken language when you need localized delivery, since the model matches speech to what you specify.
Direct One Camera Move: Request a single move like a push-in or pan so the shot stays controlled across the clip.
Keep One Speaker Focused: Center the frame on the person talking so mouth detail and voice stay tightly aligned.
Set Length to the Line: Choose a duration close to the spoken line's real pace so speech is not rushed or padded.
Example Prompts
Multilingual Spokesperson
"A friendly bank teller looks at camera and says in Spanish, 'Abrir tu cuenta toma dos minutos.' Warm branch lighting, slight smile, gentle push-in, clean synced speech with quiet office ambience."
Talking Character From an Image
"Animate the supplied illustrated fox so it turns to camera and says, 'Ready for tonight's story?' in a soft storybook voice. Cozy lamplit room, slow pan across the desk, matched lip movement."
Market Vendor Callout
"A street food vendor holds up a skewer and calls, 'Fresh off the grill, five dollars each!' Steam rising, busy stall behind, handheld camera drifting closer, lively market sound and synced voice."
Fitness Coach Count
"A coach in a bright studio faces camera and counts, 'Three, two, one, hold,' while gesturing downward. Steady frame with a slow orbit, upbeat room tone, mouth movement matched to each spoken number."
Happy Horse 1.0 vs Veo 3.1 vs Kling 2.6
Capability
Happy Horse 1.0
Veo 3.1
Kling 2.6
Synced speech and audio
✅ Built into generation
✅ Native audio
⚠️ Lip-sync as a separate step
Lip-sync accuracy
✅ Strong on spoken lines
✅ Strong
✅ Good with add-on
Multilingual delivery
✅
✅
⚠️ Limited
Clip length
3 to 15 seconds, 1s steps
Short fixed clips
Short directed clips
Resolution options
720P and 1080P
Up to 1080P
Up to 1080P
Recommended For
Voiced talking clips and localization
High-end audio-video shots
Character motion and stylized scenes
Why Choose Happy Horse 1.0 API?
Happy Horse 1.0 fits products that need people or characters to speak on camera, pairing accurate lip-sync, multilingual audio, and prompt-driven camera moves in one generation.
Through Pollo API, you reach Happy Horse 1.0 with one API key alongside 300+ leading video and image models, with clean docs, task status polling, and generation.
Happy Horse 1.0 API FAQs
What is Happy Horse 1.0?
Happy Horse 1.0 is a video generation model that creates synced audio-video clips with accurate lip-sync, multilingual speech, realistic motion, and prompt-driven camera moves.
Does Happy Horse 1.0 API support text and image inputs?
Yes. You can generate from a text prompt or animate an image URL, so both script-first and asset-first workflows run through the same model.
How does the audio and lip-sync work?
Speech and sound are generated with the video and aligned to mouth movement, so a subject's words match its lips instead of needing a separate sync pass.
What resolutions and clip lengths are available?
Happy Horse 1.0 outputs 720P or 1080P and supports clip lengths from 3 to 15 seconds, chosen one second at a time per request.
Can it produce video in multiple languages?
Yes. Prompts written in different languages generate matching spoken output for localized ads, dubbing tools, and region-specific variants.
Why run Happy Horse 1.0 through Pollo API?
Pollo API gives one integration for Happy Horse 1.0 and 300+ other models, with documentation, task tracking, and lower-cost generation.
