Google Veo2 creates high-quality image-to-video outputs with realistic motion and extensive camera controls for customizable styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$2.5per run
An elderly man with kind, smiling eyes sits on a park bench, teaching his young granddaughter how to play the ukulele. The scene is bathed in the warm, soft glow of a late afternoon golden hour. The camera slowly pushes in, capturing the genuine emotion and connection between them. Highly detailed, photorealistic.
A chubby clay fox bouncing through a colorful candyland, squishy physics, exaggerated elastic motion, stop-motion style lighting, playful soundtrack, soft shadows and texture details visible in each frame.
A dragon soaring through the clouds above a floating island kingdom, golden sunlight breaking through, feathers and embers trailing in the wind, sweeping aerial shots, orchestral background, epic cinematic atmosphere.
A lone cowboy rides across the desert at golden hour, dust trailing behind his horse, the sunlight casting long shadows on the sand, dramatic wide-angle shot, shallow depth of field, cinematic color grading
A polar bear walking slowly across melting ice floes under a cloudy arctic sky, calm ambient sounds, close-up of its breath visible in the cold air, cinematic slow motion as it looks toward the camera
Time-lapse of a city built from giant classical musical instruments (like cellos, pianos, French horns). The neck of a violin serves as a bridge, piano keys form the steps of a plaza. Vehicles are musical notes gliding along a staff. As time progresses, the sky changes from sunrise to sunset, and the light and shadows on the instrumental architecture shift accordingly.
An old man rides a rural bus alone, looking out the window at rolling fields, reflections move across his face, slow-paced, melancholic realism, vintage tones
A man paddles a canoe across a calm mountain lake at golden hour, long lens tracking shot, shimmering reflections, birds flying overhead, serene and real
A woman running along the shoreline at dusk, soft ocean waves, wide angle drone shots, skin catching golden light, immersive slow-motion sequences, real filmic tones
A young woman rides a bicycle through a sunflower field at sunset, laughing with friends, POV shots and drone overheads, lens flare and vibrant colors, upbeat indie music feel
Google Veo2 on WaveSpeedAI empowers you to create high-quality videos from both text prompts and static images, leveraging Google's advanced AI for next-generation content creation.
Veo2 on WaveSpeedAI is designed for seamless text-to-video and image-to-video generation. It understands real-world physics, human movement, and cinematic techniques, making it ideal for creators and developers who want to produce visually stunning, dynamic videos at scale.
To get the best results with Veo2 on WaveSpeedAI, try these strategies:
Close-up, two shot, over-the-shoulderMacro lens, shallow focus, wide-angle lensSci-fi, romantic comedy, action movieZoom shot, dolly shot, tracking shot, pan shotA close-up shot of melting icicles on a frozen rock wall, with cool blue tones and a zoom-in camera movement, capturing the detailed motion of water drips.
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/google/veo2 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 Veo2 below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "16:9",
"duration": 5,
"resolution": "720p",
"enable_prompt_expansion": true
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/google/veo2" \
-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
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/google/veo2";
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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "16:9",
"duration": 5,
"resolution": "720p",
"enable_prompt_expansion": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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));
}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",
"aspect_ratio": "16:9",
"duration": 5,
"resolution": "720p",
"enable_prompt_expansion": True
}
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/google/veo2", 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)Veo2 is a Google model for video generation, exposed as a REST API on WaveSpeedAI. Google Veo2 creates high-quality image-to-video outputs with realistic motion and extensive camera controls for customizable styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
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/google/google-veo2.
Veo2 starts at $2.50 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.
Key inputs: `prompt`, `aspect_ratio`, `resolution`, `duration`, `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/google/google-veo2.
Median end-to-end generation time on WaveSpeedAI is around 36 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (Google). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.