Asynchronous Generate Podcast Transcripts

POST

/302/podcast/async/text

Interfaces used in AI podcast generation tools.
Podcast generation tool experience link：https://302.ai/tools/podcast/

Price List：https://302.ai/pricing_api/

Request

Header Params

Authorization

string

optional

Example:

Bearer 302apikey

Body Params application/json

resources

array [object {2}]

生成播客内容的资料

required

type

enum<string>

素材类型

required

Allowed values:

texturlfile

content

string

素材内容或者素材的链接

required

speakerNums

integer

播客人数

required

>= 1<= 4

lang

string

播客文本的语言

required

eg：zh, en

modelName

string

模型

required

isExtract

boolean

是否值提取内容

optional

By default it is not enabled. The model will regenerate the dialogue. If enabled, the model will extract dialogue content from the input.

Default:

false

customPrompt

string

自定义额外提示词

optional

version

enum<string>

提示词版本

optional

V3 is the default prompt, while V6 is the prompt for generating long-form podcast content.

Allowed values:

v3v6

Default:

names

array[string]

自定义播客对话的虚拟人名

optional

Example

{
  "resources": [
    {
      "type": "text",
      "content": "天苍苍野茫茫风吹草动见牛羊"
    }
  ],
  "speakerNums": 2,
  "lang": "zh",
  "modelName": "gpt-4o-mini",
  "isExtract": false,
  "customPrompt": "",
  "version": "v3",
  "names": []
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.302.ai/302/podcast/async/text' \
--header 'Authorization: Bearer 302apikey' \
--header 'Content-Type: application/json' \
--data-raw '{
    "resources": [
        {
            "type": "text",
            "content": "天苍苍野茫茫风吹草动见牛羊"
        }
    ],
    "speakerNums": 2,
    "lang": "zh",
    "modelName": "gpt-4o-mini",
    "isExtract": false,
    "customPrompt": "",
    "version": "v3",
    "names": []
}'

Responses

🟢200成功

application/json

Body

task_id

string

异步任务id

required

Example

{
  "task_id": "string"
}

Fetch

Check the status of podcast text generation task