generate image
curl --request POST \
--url https://api-services.podcastor.ai/open/podcast/v1/images/generate \
--header 'Content-Type: application/json' \
--header 'X-Api-Key: <api-key>' \
--data '
{
"number_of_images": 123,
"age": "<string>",
"aspect_ratio": 123,
"avatar_library_id": 123,
"background": "<string>",
"base_photo_url": "<string>",
"detail": "<string>",
"gender": "<string>",
"lora_unique_id": "<string>",
"model": 123,
"origin": "<string>",
"photo_real": true,
"podcastTyp": 123,
"podcastVersion": 123,
"preset_style": "<string>",
"quality": "<string>",
"reference_images": [
{
"key": "<string>",
"url": "<string>"
}
],
"remix_avatar_unique_id": "<string>",
"resolution": "<string>",
"seed": 123,
"talking_pose": "<string>",
"task_from": 123
}
'import requests
url = "https://api-services.podcastor.ai/open/podcast/v1/images/generate"
payload = {
"number_of_images": 123,
"age": "<string>",
"aspect_ratio": 123,
"avatar_library_id": 123,
"background": "<string>",
"base_photo_url": "<string>",
"detail": "<string>",
"gender": "<string>",
"lora_unique_id": "<string>",
"model": 123,
"origin": "<string>",
"photo_real": True,
"podcastTyp": 123,
"podcastVersion": 123,
"preset_style": "<string>",
"quality": "<string>",
"reference_images": [
{
"key": "<string>",
"url": "<string>"
}
],
"remix_avatar_unique_id": "<string>",
"resolution": "<string>",
"seed": 123,
"talking_pose": "<string>",
"task_from": 123
}
headers = {
"X-Api-Key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'X-Api-Key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
number_of_images: 123,
age: '<string>',
aspect_ratio: 123,
avatar_library_id: 123,
background: '<string>',
base_photo_url: '<string>',
detail: '<string>',
gender: '<string>',
lora_unique_id: '<string>',
model: 123,
origin: '<string>',
photo_real: true,
podcastTyp: 123,
podcastVersion: 123,
preset_style: '<string>',
quality: '<string>',
reference_images: [{key: '<string>', url: '<string>'}],
remix_avatar_unique_id: '<string>',
resolution: '<string>',
seed: 123,
talking_pose: '<string>',
task_from: 123
})
};
fetch('https://api-services.podcastor.ai/open/podcast/v1/images/generate', 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-services.podcastor.ai/open/podcast/v1/images/generate",
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([
'number_of_images' => 123,
'age' => '<string>',
'aspect_ratio' => 123,
'avatar_library_id' => 123,
'background' => '<string>',
'base_photo_url' => '<string>',
'detail' => '<string>',
'gender' => '<string>',
'lora_unique_id' => '<string>',
'model' => 123,
'origin' => '<string>',
'photo_real' => true,
'podcastTyp' => 123,
'podcastVersion' => 123,
'preset_style' => '<string>',
'quality' => '<string>',
'reference_images' => [
[
'key' => '<string>',
'url' => '<string>'
]
],
'remix_avatar_unique_id' => '<string>',
'resolution' => '<string>',
'seed' => 123,
'talking_pose' => '<string>',
'task_from' => 123
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"X-Api-Key: <api-key>"
],
]);
$response = curl_exec($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-services.podcastor.ai/open/podcast/v1/images/generate"
payload := strings.NewReader("{\n \"number_of_images\": 123,\n \"age\": \"<string>\",\n \"aspect_ratio\": 123,\n \"avatar_library_id\": 123,\n \"background\": \"<string>\",\n \"base_photo_url\": \"<string>\",\n \"detail\": \"<string>\",\n \"gender\": \"<string>\",\n \"lora_unique_id\": \"<string>\",\n \"model\": 123,\n \"origin\": \"<string>\",\n \"photo_real\": true,\n \"podcastTyp\": 123,\n \"podcastVersion\": 123,\n \"preset_style\": \"<string>\",\n \"quality\": \"<string>\",\n \"reference_images\": [\n {\n \"key\": \"<string>\",\n \"url\": \"<string>\"\n }\n ],\n \"remix_avatar_unique_id\": \"<string>\",\n \"resolution\": \"<string>\",\n \"seed\": 123,\n \"talking_pose\": \"<string>\",\n \"task_from\": 123\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("X-Api-Key", "<api-key>")
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-services.podcastor.ai/open/podcast/v1/images/generate")
.header("X-Api-Key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"number_of_images\": 123,\n \"age\": \"<string>\",\n \"aspect_ratio\": 123,\n \"avatar_library_id\": 123,\n \"background\": \"<string>\",\n \"base_photo_url\": \"<string>\",\n \"detail\": \"<string>\",\n \"gender\": \"<string>\",\n \"lora_unique_id\": \"<string>\",\n \"model\": 123,\n \"origin\": \"<string>\",\n \"photo_real\": true,\n \"podcastTyp\": 123,\n \"podcastVersion\": 123,\n \"preset_style\": \"<string>\",\n \"quality\": \"<string>\",\n \"reference_images\": [\n {\n \"key\": \"<string>\",\n \"url\": \"<string>\"\n }\n ],\n \"remix_avatar_unique_id\": \"<string>\",\n \"resolution\": \"<string>\",\n \"seed\": 123,\n \"talking_pose\": \"<string>\",\n \"task_from\": 123\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api-services.podcastor.ai/open/podcast/v1/images/generate")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["X-Api-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"number_of_images\": 123,\n \"age\": \"<string>\",\n \"aspect_ratio\": 123,\n \"avatar_library_id\": 123,\n \"background\": \"<string>\",\n \"base_photo_url\": \"<string>\",\n \"detail\": \"<string>\",\n \"gender\": \"<string>\",\n \"lora_unique_id\": \"<string>\",\n \"model\": 123,\n \"origin\": \"<string>\",\n \"photo_real\": true,\n \"podcastTyp\": 123,\n \"podcastVersion\": 123,\n \"preset_style\": \"<string>\",\n \"quality\": \"<string>\",\n \"reference_images\": [\n {\n \"key\": \"<string>\",\n \"url\": \"<string>\"\n }\n ],\n \"remix_avatar_unique_id\": \"<string>\",\n \"resolution\": \"<string>\",\n \"seed\": 123,\n \"talking_pose\": \"<string>\",\n \"task_from\": 123\n}"
response = http.request(request)
puts response.read_body{
"cause": "<string>",
"code": 123,
"data": {},
"details": "<unknown>",
"msg": "<string>",
"rid": "<string>"
}Media assets
Generate image
Generate Podcast images using Web pricing. Set source to podcast_background for a background or podcast_cover for covers; poll get_image_task.
POST
/
open
/
podcast
/
v1
/
images
/
generate
generate image
curl --request POST \
--url https://api-services.podcastor.ai/open/podcast/v1/images/generate \
--header 'Content-Type: application/json' \
--header 'X-Api-Key: <api-key>' \
--data '
{
"number_of_images": 123,
"age": "<string>",
"aspect_ratio": 123,
"avatar_library_id": 123,
"background": "<string>",
"base_photo_url": "<string>",
"detail": "<string>",
"gender": "<string>",
"lora_unique_id": "<string>",
"model": 123,
"origin": "<string>",
"photo_real": true,
"podcastTyp": 123,
"podcastVersion": 123,
"preset_style": "<string>",
"quality": "<string>",
"reference_images": [
{
"key": "<string>",
"url": "<string>"
}
],
"remix_avatar_unique_id": "<string>",
"resolution": "<string>",
"seed": 123,
"talking_pose": "<string>",
"task_from": 123
}
'import requests
url = "https://api-services.podcastor.ai/open/podcast/v1/images/generate"
payload = {
"number_of_images": 123,
"age": "<string>",
"aspect_ratio": 123,
"avatar_library_id": 123,
"background": "<string>",
"base_photo_url": "<string>",
"detail": "<string>",
"gender": "<string>",
"lora_unique_id": "<string>",
"model": 123,
"origin": "<string>",
"photo_real": True,
"podcastTyp": 123,
"podcastVersion": 123,
"preset_style": "<string>",
"quality": "<string>",
"reference_images": [
{
"key": "<string>",
"url": "<string>"
}
],
"remix_avatar_unique_id": "<string>",
"resolution": "<string>",
"seed": 123,
"talking_pose": "<string>",
"task_from": 123
}
headers = {
"X-Api-Key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'X-Api-Key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
number_of_images: 123,
age: '<string>',
aspect_ratio: 123,
avatar_library_id: 123,
background: '<string>',
base_photo_url: '<string>',
detail: '<string>',
gender: '<string>',
lora_unique_id: '<string>',
model: 123,
origin: '<string>',
photo_real: true,
podcastTyp: 123,
podcastVersion: 123,
preset_style: '<string>',
quality: '<string>',
reference_images: [{key: '<string>', url: '<string>'}],
remix_avatar_unique_id: '<string>',
resolution: '<string>',
seed: 123,
talking_pose: '<string>',
task_from: 123
})
};
fetch('https://api-services.podcastor.ai/open/podcast/v1/images/generate', 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-services.podcastor.ai/open/podcast/v1/images/generate",
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([
'number_of_images' => 123,
'age' => '<string>',
'aspect_ratio' => 123,
'avatar_library_id' => 123,
'background' => '<string>',
'base_photo_url' => '<string>',
'detail' => '<string>',
'gender' => '<string>',
'lora_unique_id' => '<string>',
'model' => 123,
'origin' => '<string>',
'photo_real' => true,
'podcastTyp' => 123,
'podcastVersion' => 123,
'preset_style' => '<string>',
'quality' => '<string>',
'reference_images' => [
[
'key' => '<string>',
'url' => '<string>'
]
],
'remix_avatar_unique_id' => '<string>',
'resolution' => '<string>',
'seed' => 123,
'talking_pose' => '<string>',
'task_from' => 123
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"X-Api-Key: <api-key>"
],
]);
$response = curl_exec($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-services.podcastor.ai/open/podcast/v1/images/generate"
payload := strings.NewReader("{\n \"number_of_images\": 123,\n \"age\": \"<string>\",\n \"aspect_ratio\": 123,\n \"avatar_library_id\": 123,\n \"background\": \"<string>\",\n \"base_photo_url\": \"<string>\",\n \"detail\": \"<string>\",\n \"gender\": \"<string>\",\n \"lora_unique_id\": \"<string>\",\n \"model\": 123,\n \"origin\": \"<string>\",\n \"photo_real\": true,\n \"podcastTyp\": 123,\n \"podcastVersion\": 123,\n \"preset_style\": \"<string>\",\n \"quality\": \"<string>\",\n \"reference_images\": [\n {\n \"key\": \"<string>\",\n \"url\": \"<string>\"\n }\n ],\n \"remix_avatar_unique_id\": \"<string>\",\n \"resolution\": \"<string>\",\n \"seed\": 123,\n \"talking_pose\": \"<string>\",\n \"task_from\": 123\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("X-Api-Key", "<api-key>")
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-services.podcastor.ai/open/podcast/v1/images/generate")
.header("X-Api-Key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"number_of_images\": 123,\n \"age\": \"<string>\",\n \"aspect_ratio\": 123,\n \"avatar_library_id\": 123,\n \"background\": \"<string>\",\n \"base_photo_url\": \"<string>\",\n \"detail\": \"<string>\",\n \"gender\": \"<string>\",\n \"lora_unique_id\": \"<string>\",\n \"model\": 123,\n \"origin\": \"<string>\",\n \"photo_real\": true,\n \"podcastTyp\": 123,\n \"podcastVersion\": 123,\n \"preset_style\": \"<string>\",\n \"quality\": \"<string>\",\n \"reference_images\": [\n {\n \"key\": \"<string>\",\n \"url\": \"<string>\"\n }\n ],\n \"remix_avatar_unique_id\": \"<string>\",\n \"resolution\": \"<string>\",\n \"seed\": 123,\n \"talking_pose\": \"<string>\",\n \"task_from\": 123\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api-services.podcastor.ai/open/podcast/v1/images/generate")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["X-Api-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"number_of_images\": 123,\n \"age\": \"<string>\",\n \"aspect_ratio\": 123,\n \"avatar_library_id\": 123,\n \"background\": \"<string>\",\n \"base_photo_url\": \"<string>\",\n \"detail\": \"<string>\",\n \"gender\": \"<string>\",\n \"lora_unique_id\": \"<string>\",\n \"model\": 123,\n \"origin\": \"<string>\",\n \"photo_real\": true,\n \"podcastTyp\": 123,\n \"podcastVersion\": 123,\n \"preset_style\": \"<string>\",\n \"quality\": \"<string>\",\n \"reference_images\": [\n {\n \"key\": \"<string>\",\n \"url\": \"<string>\"\n }\n ],\n \"remix_avatar_unique_id\": \"<string>\",\n \"resolution\": \"<string>\",\n \"seed\": 123,\n \"talking_pose\": \"<string>\",\n \"task_from\": 123\n}"
response = http.request(request)
puts response.read_body{
"cause": "<string>",
"code": 123,
"data": {},
"details": "<unknown>",
"msg": "<string>",
"rid": "<string>"
}MCP tool:
podcast_generate_image. OAuth scope: podcast.generate.Authorizations
Headers
Replay a completed identical request without repeating side effects.
Maximum string length:
128Body
application/json
请求体
生成图片张数 1-4
年纪
宽高比 0:9比16/1:16比9/2:1比1；podcast_cover 额外支持 3:3比4/4:4比3
avatar_library 表ID
数字人类型，可选，不传默认 default；支持 default/pet/cartoon
Available options:
default, pet, cartoon 提示词，长度上限1500英文字符
基础图片（向后兼容，建议使用 reference_images）
生图提示词，最多16000个Unicode字符
Maximum string length:
16000性别
lora 模型 id
模型: 1:modern-flair/2:timeless-charm
人种
真实感开关：true-开启；false-关闭
对话数字人类型 0:默认值，非对话数字人/1:左/2:右
podcast版本 目前有效值为 10 和 20
风格
生图质量 medium/high，仅 gpt-image2 使用
参考图列表
Show child attributes
Show child attributes
remix ugcAvatar 表的 uniqueId
生图分辨率 1K/2K/4K
随机种子
来源，目前支持 podcast/background/image/podcast_background/podcast_cover
Available options:
podcast, background, image, podcast_background, podcast_cover 提示词，长度上限1500英文字符
任务来源：1-aigc;3-packs;99-代表工具生成，无需扣费和队列限制
Podcast 背景分类；source=podcast_background 时必填，0:Speaker Focus/2:Alternating shots
Available options:
0, 2