WAN 3.0 is LIVE — 30s in one shot | Try in Video Generator →
Home/Explore/Alibaba/Wan 2.5/Text To Video Fast

alibaba/

WAN 2.5 Fast creates synchronized-audio videos from text or images in 720p, faster and more affordable than Google Veo3. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-video
Input

Idle

$0.34per run·~29 / $10

Next:

ExamplesView all

A graceful ballerina with blonde hair, blue eyes, and a noble presence. Style: Cinematic, soft lighting, delicate textures, resembling a high-end perfume commercial. Wardrobe: A simple, elegant white silk dress that flows with her movements. Setting: An empty, minimalist modern art gallery with vast floor-to-ceiling windows and gray concrete walls. Action: Barefoot, she dances to a gentle piano melody, her movements are fluid, expressive, and full of emotional tension, incorporating elegant spins and leaps. Shot: Smooth dolly zoom from a wide shot to a close-up, using a shallow depth of field to isolate the subject. Lighting: Soft, natural light pours in from the windows, creating a beautiful halo effect and a serene, artistic, and almost sacred atmosphere. Voice-over (Optional): (A soft, gentle narration) "Every movement is a poem of the soul."

一个穿风衣的男人深吸了一口烟,帅气

In the style of a 1920s black and white silent film, a dramatic actress in vintage clothing at a train station. Her expressions are exaggerated and theatrical as she tearfully mouths a goodbye to her lover. The scene then cuts to an art deco title card that reads: "My Dearest, I must go. Do not forget me." The image has film grain and scratches, accompanied by a piano score.

A young woman, with tears welling up in her eyes, her voice trembling but firm as she says "I love you", close-up shot, romantic sunset in the background, soft lighting, cinematic.

A ruggedly handsome man with a muscular build, intricate tattoos on his arms, and a defiant look in his eyes. Style: Gritty, grainy black and white film style; raw and powerful. Wardrobe: A tight, worn-out white t-shirt under a scuffed black leather jacket and ripped denim jeans. Setting: A deserted highway at sunset, with a vintage Harley-Davidson motorcycle parked beside him. Action: He leans against his motorcycle, pulls a cigarette from his pocket, lights it, takes a long drag, and slowly exhales smoke. He gazes toward the distant horizon, his expression resolute and free. Shot: A low-angle shot looking up, emphasizing his commanding presence. Lighting: The setting sun acts as a backlight, outlining his figure in gold. The mood is one of freedom, rebellion, and a touch of loneliness. Voice-over (Optional): (Sound of a motorcycle engine revving, followed by the sound of the wind.)

A confident woman with vibrant-colored braids, performing a high-energy hip-hop dance routine in the middle of a bustling intersection like Shibuya Crossing. She's wearing stylish, baggy streetwear. The crowd around her is a motion blur, making her the sharp focus of the scene. Neon lights from the surrounding buildings reflect off the wet pavement. The camera uses dynamic, low-angle shots and quick cuts synchronized to the beat of a powerful trap song. Energetic, urban, rebellious.

In a vast, gothic library lit only by a single green banker's lamp, a handsome, mysterious man with sharp cheekbones and glasses is intently reading an ancient, leather-bound book. He absently runs a hand through his dark, wavy hair. Shadows play across his face, obscuring his expression just enough to create intrigue. A close-up shot focuses on his long fingers tracing the old script on the page. The atmosphere is silent, intellectual, and slightly melancholic. "Dark Academia" aesthetic.

Studio Ghibli-inspired anime style. A young girl with a straw hat lies peacefully in a sun-dappled magical forest, surrounded by friendly, glowing forest spirits (Kodama). A gentle breeze rustles the leaves of the giant, ancient trees. The air is filled with sparkling dust motes, illuminated by shafts of sunlight. The art style is soft, with a hand-painted watercolor texture. The scene feels serene, magical, and heartwarming.

A vibrant and joyful woman with curly dark hair and a colorful ruffled dress, dancing an energetic Salsa with a partner in the middle of a lively street festival in Havana, Cuba. The air is warm and filled with confetti. The street is crowded with smiling people, and a live band is playing enthusiastically in the background. The lighting comes from strings of festive lights hung between colonial-style buildings. The camera spins with the dancers, capturing the dizzying, joyful motion and the genuine smiles on their faces. High energy, cinematic, warm colors.

Related Models

README

WAN 2.5 Text-to-Video Model

WAN 2.5 is an advanced text-to-video model provided by Cloud's DashScope platform. This model generates high-quality 480p/720p/1080p videos from text prompts.

What makes it stand out?

  • More affordable: Wan 2.5 is more streamlined and cost-effective - reducing creator expenses and offering more options.
  • One-pass A/V sync: Wan 2.5 creates a fully synchronized video (audio/voiceover + lip-sync) from a single, well-structured prompt - no separate recording or manual alignment required.
  • Multilingual friendly: Wan 2.5 reliably processes like Chinese prompts for A/V-synced videos.
  • Longer duration & more video size options: Wan 2.5 delivers up to 10 seconds and 6 aspect/size options, enabling more storytelling room and publishing flexibility.
  • Custom Voice: Add your own audio or let the model generate one for you. Plug-and-play, easy to swap!

Designed For

  • Marketing teams: Fast, polished demos/tutorials—low cost, consistent style.
  • Global enterprises: Multilingual, lip-synced videos with subtitles for efficient localization.
  • Storytellers & YouTubers: Immersive narratives while maintaining cadence and quality—driving growth.
  • Corporate training teams: HD videos over docs—clearer key points, better communication.

Pricing

ResolutionPrice per second
720p$0.068
1080p$0.102

How to Use

  1. Write your prompt.
  2. Upload an audio file (optional) for voice/music.
  3. Choose the video size (resolution/aspect).
  4. Select the video duration (e.g., 5s / 10s).
  5. Submit and wait for processing.
  6. Preview and download the result.

Note

Audio limits

  • Formats: wav, mp3
  • Length: 3–30 seconds
  • File size: ≤ 15 MB

Over-limit handling

  • If the audio exceeds the target duration (5s or 10s), the model keeps only the first 5s/10s; the rest is discarded.
  • If the audio is shorter than the video duration, the extra video part is silent.
Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Wan 2.5 Text To Video Fast API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/alibaba/wan-2.5/text-to-video-fast with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Wan 2.5 Text To Video Fast below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "size": "1280*720",
    "duration": 5,
    "enable_prompt_expansion": false,
    "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.5/text-to-video-fast" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/alibaba/wan-2.5/text-to-video-fast";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "size": "1280*720",
        "duration": 5,
        "enable_prompt_expansion": false,
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "size": "1280*720",
    "duration": 5,
    "enable_prompt_expansion": False,
    "seed": -1
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/alibaba/wan-2.5/text-to-video-fast", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Wan 2.5 Text To Video Fast API — Frequently asked questions

What is the Wan 2.5 Text To Video Fast API?

Wan 2.5 Text To Video Fast is a Alibaba model for video generation, exposed as a REST API on WaveSpeedAI. WAN 2.5 Fast creates synchronized-audio videos from text or images in 720p, faster and more affordable than Google Veo3. 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 Wan 2.5 Text To Video Fast 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 result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/alibaba/alibaba-wan-2.5-text-to-video-fast.

How much does Wan 2.5 Text To Video Fast cost per run?

Wan 2.5 Text To Video Fast starts at $0.34 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 Wan 2.5 Text To Video Fast accept?

Key inputs: `prompt`, `audio`, `duration`, `size`, `seed`, `negative_prompt`. 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/alibaba/alibaba-wan-2.5-text-to-video-fast.

How long does Wan 2.5 Text To Video Fast take to generate?

Median end-to-end generation time on WaveSpeedAI is around 226 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Wan 2.5 Text To Video Fast outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Alibaba). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.