Hunyuan Video (t2v) is an advanced text-to-video model that generates high-quality videos from text prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.4per run·~25 / $10
ExamplesView all
A ballerina dancing in an abandoned theater, spotlight follows her movements, dramatic angles, particles of dust in the air, emotional climax
A playful, fluffy orange kitten wearing sunglasses skateboarding smoothly through a neon-lit futuristic cityscape at night, passing robots, flying cars, and holographic advertisements.
two cats
a girl
A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots, and carries a black purse.
A cute cartoon cat, wearing a mini chef's hat, clumsily attempting to bake a cake, flour splattered everywhere, finally succeeding in making a wobbly cake and happily licking its mouth.
An elderly artist with graying hair, dressed in a paint-stained linen shirt, sitting in front of an antique wooden easel, gazing deeply at the canvas. The studio is softly lit, with a serene French countryside view outside the window.
A six-year-old girl, wearing a bright yellow raincoat, happily jumping in the rain, with water splashing around her. A pure smile is on her face, and the background is a lush green park with post-rain sunlight breaking through the clouds.
A classical pianist, dressed in a sleek black gown, performing with intense focus on a grand stage. Her fingers dance gracefully across the keys of a polished grand piano, bathed in warm spotlight, with an ornate concert hall audience softly visible in the shadows.
An elderly woman, her face crinkled with warmth, gently tending to a vibrant rose bush in a cottage garden. She wears a wide-brimmed straw hat and a floral apron. Bees buzz lazily in the soft afternoon light, and colorful flowers fill the background, creating a serene and joyful atmosphere.
A brilliant scientist, mid-40s, with disheveled hair and intense curiosity in their eyes, hunched over a microscope in a dimly lit laboratory. Flasks bubble softly in the background, illuminated by an eerie green glow, emphasizing a sense of discovery and late-night work.
An animated scene featuring a dynamic teenage boy with spiky blue hair and vibrant eyes, standing confidently on a futuristic city rooftop at dusk. Neon lights flicker in the background, casting colorful glows on his detailed anime-style outfit with intricate patterns. The scene captures his energetic pose with dramatic camera angles — from low-angle close-ups to sweeping panoramic shots. His expression is fierce but determined, with wind effects animating his hair and coat. The video flows with fluid motion and bright saturated colors, evoking a sense of adventure and youthful spirit.
A pixel art style character — a retro-style warrior girl with a red scarf and pixelated sword — stands on a colorful, blocky medieval landscape. The animation includes pixel-perfect movements of her walking and readying for battle, with simple but expressive facial animations. The background features pixel trees and castles, with pixel fireflies fluttering around. The video has a nostalgic 8-bit game vibe, with chiptune music cues and smooth pixel transitions, capturing a playful and charming adventure atmosphere.
A young person wearing a cyberpunk-style helmet, their body enveloped in neon reflections, sits within a virtual reality space filled with data streams and holographic projections. Their fingertips lightly touch floating lines of code, and their eyes show a mix of bewilderment and entrancement.
Related Models
README
Hunyuan Video Text-to-Video
Transform your ideas into stunning videos with Hunyuan Video Text-to-Video. This state-of-the-art model from Tencent generates high-quality 720p videos directly from text descriptions — bringing your imagination to life with smooth motion and cinematic visuals.
Why It Stands Out
- Pure text-to-video generation: No source image required — simply describe your vision and watch it unfold.
- HD output: Generate crisp 1280×720 videos with rich detail and visual clarity.
- Prompt Enhancer: Built-in AI-powered prompt optimization helps craft better descriptions for improved results.
- Smooth motion: Advanced temporal modeling ensures natural, fluid movement across frames.
- Flexible sizing: Multiple aspect ratio options to fit your content needs.
- Reproducibility: Use the seed parameter to recreate exact results or explore variations.
Pricing
| Output | Price |
|---|---|
| Per video | $0.40 |
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the video you want to generate. |
| size | No | Output resolution (default: 1280×720). |
| seed | No | Set for reproducibility; -1 for random. |
| num_inference_steps | No | Quality/speed trade-off (default: 30). |
How to Use
- Write a prompt describing the scene, characters, action, and style you want. Use the Prompt Enhancer for AI-assisted optimization.
- Select size — choose the aspect ratio that fits your content.
- Adjust inference steps — higher values may improve quality at the cost of speed.
- Set a seed (optional) for reproducible results.
- Click Run and wait for your video to generate.
- Preview and download the result.
Best Use Cases
- Social Media Content — Create viral-worthy video clips for TikTok, Reels, and Shorts.
- Marketing & Advertising — Produce concept videos and promotional content without filming.
- Storytelling & Animation — Generate scenes for short films, music videos, or creative projects.
- Game & App Previews — Create cinematic trailers and gameplay concepts from descriptions.
- Educational Content — Visualize complex concepts and scenarios for learning materials.
Pro Tips for Best Quality
- Be detailed in your prompt — describe subject, action, environment, lighting, mood, and camera movement.
- Include style keywords like "cinematic," "realistic," "anime," or "futuristic" to guide the aesthetic.
- Start with lower inference steps for quick previews, then increase for final renders.
- Fix the seed when iterating to compare the effect of different prompt adjustments.
- Keep prompts focused — overly complex descriptions may dilute the output quality.
Notes
- Processing time varies based on current queue load.
- Please ensure your prompts comply with content guidelines.
Hunyuan Video T2v API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan-video/t2v with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Hunyuan Video T2v below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan-video/t2v" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"seed": -1,
"num_inference_steps": 30
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("wavespeed-ai/hunyuan-video/t2v", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"seed": -1,
"num_inference_steps": 30
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/hunyuan-video/t2v",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"seed": -1,
"num_inference_steps": 30
}
)
print(output["outputs"][0]) # → URL of the generated outputHunyuan Video T2v API — Frequently asked questions
What is the Hunyuan Video T2v API?
Hunyuan Video T2v is a WaveSpeedAI model for video generation, exposed as a REST API on WaveSpeedAI. Hunyuan Video (t2v) is an advanced text-to-video model that generates high-quality videos from text prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Hunyuan Video T2v API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/hunyuan-video-t2v.
How much does Hunyuan Video T2v cost per run?
Hunyuan Video T2v starts at $0.40 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Hunyuan Video T2v accept?
Key inputs: `prompt`, `size`, `seed`, `num_inference_steps`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/hunyuan-video-t2v.
How long does Hunyuan Video T2v take to generate?
Average end-to-end generation time on WaveSpeedAI is around 76 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Hunyuan Video T2v outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.