curl --request POST \
--url https://api.evolink.ai/v1/videos/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "sora-2-preview",
"prompt": "A cat playing piano"
}
'import requests
url = "https://api.evolink.ai/v1/videos/generations"
payload = {
"model": "sora-2-preview",
"prompt": "A cat playing piano"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({model: 'sora-2-preview', prompt: 'A cat playing piano'})
};
fetch('https://api.evolink.ai/v1/videos/generations', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.evolink.ai/v1/videos/generations",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'model' => 'sora-2-preview',
'prompt' => 'A cat playing piano'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.evolink.ai/v1/videos/generations"
payload := strings.NewReader("{\n \"model\": \"sora-2-preview\",\n \"prompt\": \"A cat playing piano\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.evolink.ai/v1/videos/generations")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"sora-2-preview\",\n \"prompt\": \"A cat playing piano\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.evolink.ai/v1/videos/generations")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"model\": \"sora-2-preview\",\n \"prompt\": \"A cat playing piano\"\n}"
response = http.request(request)
puts response.read_body{
"created": 1757169743,
"id": "task-unified-1757169743-7cvnl5zw",
"model": "sora-2-preview",
"object": "video.generation.task",
"progress": 0,
"status": "pending",
"task_info": {
"can_cancel": true,
"estimated_time": 300,
"video_duration": 9
},
"type": "video",
"usage": {
"billing_rule": "per_call",
"credits_reserved": 7,
"user_group": "default"
}
}{
"error": {
"code": "invalid_request",
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}{
"error": {
"code": "unauthorized",
"message": "Invalid or expired token",
"type": "authentication_error"
}
}{
"error": {
"code": "insufficient_quota",
"message": "Insufficient quota. Please top up your account.",
"type": "insufficient_quota"
}
}{
"error": {
"code": "model_access_denied",
"message": "Token does not have access to model: sora-2-preview",
"type": "invalid_request_error"
}
}{
"error": {
"code": "rate_limit_exceeded",
"message": "Too many requests, please try again later",
"type": "rate_limit_error"
}
}{
"error": {
"code": "internal_error",
"message": "Internal server error",
"type": "api_error"
}
}Sora-2 Generación de video
- Sora 2 Preview (sora-2-preview) admite texto a video, imagen a video y más
- Procesamiento asíncrono, use el ID de tarea devuelto para consultar estado
- Los enlaces de video generados son válidos durante 24 horas, guárdelos de inmediato
Nota:
- Sora2 tiene una moderación de contenido muy estricta, las tareas pueden fallar debido a esto
- No se admiten imágenes de personas reales
curl --request POST \
--url https://api.evolink.ai/v1/videos/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "sora-2-preview",
"prompt": "A cat playing piano"
}
'import requests
url = "https://api.evolink.ai/v1/videos/generations"
payload = {
"model": "sora-2-preview",
"prompt": "A cat playing piano"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({model: 'sora-2-preview', prompt: 'A cat playing piano'})
};
fetch('https://api.evolink.ai/v1/videos/generations', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.evolink.ai/v1/videos/generations",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'model' => 'sora-2-preview',
'prompt' => 'A cat playing piano'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.evolink.ai/v1/videos/generations"
payload := strings.NewReader("{\n \"model\": \"sora-2-preview\",\n \"prompt\": \"A cat playing piano\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.evolink.ai/v1/videos/generations")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"sora-2-preview\",\n \"prompt\": \"A cat playing piano\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.evolink.ai/v1/videos/generations")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"model\": \"sora-2-preview\",\n \"prompt\": \"A cat playing piano\"\n}"
response = http.request(request)
puts response.read_body{
"created": 1757169743,
"id": "task-unified-1757169743-7cvnl5zw",
"model": "sora-2-preview",
"object": "video.generation.task",
"progress": 0,
"status": "pending",
"task_info": {
"can_cancel": true,
"estimated_time": 300,
"video_duration": 9
},
"type": "video",
"usage": {
"billing_rule": "per_call",
"credits_reserved": 7,
"user_group": "default"
}
}{
"error": {
"code": "invalid_request",
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}{
"error": {
"code": "unauthorized",
"message": "Invalid or expired token",
"type": "authentication_error"
}
}{
"error": {
"code": "insufficient_quota",
"message": "Insufficient quota. Please top up your account.",
"type": "insufficient_quota"
}
}{
"error": {
"code": "model_access_denied",
"message": "Token does not have access to model: sora-2-preview",
"type": "invalid_request_error"
}
}{
"error": {
"code": "rate_limit_exceeded",
"message": "Too many requests, please try again later",
"type": "rate_limit_error"
}
}{
"error": {
"code": "internal_error",
"message": "Internal server error",
"type": "api_error"
}
}Autorizaciones
##Todas las APIs requieren autenticación Bearer Token##
Obtener API Key:
Visita la Página de gestión de API Key para obtener tu API Key
Agregar al encabezado de la solicitud:
Authorization: Bearer YOUR_API_KEY
Cuerpo
Nombre del modelo de generación de video
"sora-2-preview"
Prompt que describe el video a generar, máximo 5000 tokens
5000"A cat playing piano"
Relación de aspecto del video. 1280x720 genera video horizontal, 720x1280 genera video vertical
1280x720, 720x1280, 16:9, 9:16 "16:9"
Duración del video (segundos), por defecto 4
Nota:
- Solo admite
4,8,12segundos - Mayor duración tiene un costo más alto
4
URLs de imágenes de referencia para imagen a video
Nota:
- No se admiten imágenes de personas reales
- Máximo 1 imagen por solicitud
- Tamaño máximo: 10MB
- Formatos: .jpg, .jpeg, .png, .webp
- Las dimensiones en píxeles de la imagen deben coincidir exactamente con el aspect_ratio seleccionado (por ejemplo, si aspect_ratio es
1280x720, la imagen cargada debe ser exactamente de 1280x720 píxeles) - La URL de la imagen debe ser directamente accesible por el servidor, o activar la descarga al acceder (normalmente URLs que terminan con extensiones de imagen como .png, .jpg)
1["http://example.com/image1.jpg"]
URL de callback HTTPS para la finalización de la tarea
Momento del callback:
- Se activa cuando la tarea se completa, falla o se cancela
- Se envía después de la confirmación de facturación
Restricciones de seguridad:
- Solo protocolo HTTPS
- No se permiten direcciones IP privadas (127.0.0.1, 10.x.x.x, 172.16-31.x.x, 192.168.x.x, etc.)
- Longitud máxima de URL: 2048 caracteres
Mecanismo de callback:
- Tiempo de espera: 10 segundos
- Máximo 3 reintentos en caso de fallo (a intervalos de 1s/2s/4s)
- El formato de respuesta coincide con la API de consulta de tareas
- Código de estado 2xx = éxito, otros códigos activan reintento
"https://your-domain.com/webhooks/video-task-completed"
Respuesta
Tarea de generación de video creada exitosamente
Marca de tiempo de creación de la tarea
1757169743
ID de tarea
"task-unified-1757169743-7cvnl5zw"
Nombre del modelo utilizado
"sora-2-preview"
Tipo de tarea
video.generation.task Progreso de la tarea (0-100)
0 <= x <= 1000
Estado de la tarea
pending, processing, completed, failed "pending"
Show child attributes
Show child attributes
Tipo de salida
text, image, audio, video "video"
Show child attributes
Show child attributes