Enterprise AI Resource Hub - 302.AI | Pay-as-you-go, Comprehensive AI model API Access, Instant Online App Usage

cicada3.0

Audio generation service from Chanjing

2025-06-20

Audio-Video Processing

Pricing:

$0.001/second

Bulk order? Contact your manager for exclusive deals

API Overview

Audio generation service from Chanjing

API Console

API Reference (5)

API Description API Endpoint Request Method Stability Parameter Description

Create a language generation task

https://api.302.ai/chanjing/open/v1/create_audio_task

POST

Stable

View Details

Document Details

Reference: https://alidocs.dingtalk.com/i/nodes/QOG9lyrgJP3Qp73mHnE1MQ4YVzN67Mw4
Price: cicada1.0 0.0006 PTC/second audio, cicada3.0 0.001 PTC/second audio
Parameters are as follows:

Parameter Name	Type	Nested Key	Required	Example
audio_man	string		Yes	f6254806192e4ef99189ae899d89943e
speed	number		Yes	1
pitch	number		Yes	1
volume	number		Yes	100
text	object		Yes
		text	Yes	Hello, I am your Cicada Digital Human (text length limit below 4000 characters)
		plain_text	No	Hello, I am your Cicada Digital Human
font_size	number		No	64
width	number		No	1000
height	number		No	90

Request Parameters

Header Parameters

Authorizationstring

Optional

Example Value:Bearer {{YOUR_API_KEY}}

Request Body application/json

audio_manstring

Required

speedinteger

Required

pitchinteger

Required

volumeinteger

Required

textobject

Required

font_sizeinteger

Optional

widthinteger

Optional

heightinteger

Optional

callbackstring

Optional

Retrieve speech synthesis results

https://api.302.ai/chanjing/open/v1/audio_task_state

POST

Stable

View Details

Document Details

Primary Field	Secondary Field	Tertiary Field	Description
code			Response status code
msg			Response message
data	id		Video ID
	type		Voice type
	status		Status: 10 Generating, 9 Generated (includes success and failure)
	text		Voice text
	full	url	Standard frequency link
		path	Standard frequency address
		duration	Standard frequency duration
	slice		Slice
	errMsg		Error message
	errReason		Error reason
	subtitles (array type)	key	Subtitle key value
		start_time	Subtitle start time
		end_time	Subtitle end time
		subtitle	Subtitle text

Request Parameters

Header Parameters

Authorizationstring

Optional

Example Value:Bearer {{YOUR_API_KEY}}

Request Body application/json

task_idstring

Required

Create a voice customization task

https://api.302.ai/chanjing/open/v1/create_customised_audio

POST

Stable

View Details

Document Details

Reference: https://alidocs.dingtalk.com/i/nodes/AR4GpnMqJzM6gPMwuoalO5ZRVKe0xjE3

Request Parameters Body

Field	Type	Required	Description
name	String	Yes	Voice name
url	String	Yes	Voice link, supports mp3, wav, m4a. Recording environment must be quiet, no background noise, normal speaking speed, clear voice, continuous speech for at least 8 seconds, preferably with emotional expression. Duration: 30 seconds to 5 minutes, file size not exceeding 100MB
model_type	Model Type	No	Default model is cicada1.0, supports cicada1.0, cicada3.0
language	Language	No	Default is cn (Chinese), supports en (English). Other languages are not supported currently. For special language requirements, please contact customer service.
text	String	No	Voice preview text, content must not exceed 50 characters
callback	String	No	Callback URL, task results will be sent to this address via a POST request. The request body output is the same as the data returned by the voice details query

Request Parameters

Header Parameters

Authorizationstring

Optional

Example Value:Bearer {{YOUR_API_KEY}}

Request Body application/json

namestring

Required

urlstring

Required

callbackstring

Required

Retrieve voice customization results

https://api.302.ai/chanjing/open/v1/customised_audio

GET

Stable

View Details

Document Details

Reference: https://alidocs.dingtalk.com/i/nodes/ydxXB52LJq7yOZ7zuEMY2vYzWqjMp697

Response Fields Description

Primary Field	Secondary Field	Description
code		Response status code
msg		Response message
data	id	Voice ID
	progress	Task progress 0-100
	type	Voice model type (cicada1.0, cicada3.0)
	name	Voice name
	err_msg	Error message for exceptions or failures
	audio_path	Training audio segment (valid segment extracted from the original audio for training)
	status	Production status: 1 In progress, 2 Completed, 3 Expired, 4 Failed, 99 Deleted

Request Parameters

Header Parameters

Authorizationstring

Optional

Example Value:Bearer {{YOUR_API_KEY}}

Query Parameters

idstring

Optional

Example Value:C-Audio-ac568092f7bb4bb0980a8100dacb80d1

Delete customized voice

https://api.302.ai/chanjing/open/v1/delete_customised_audio

POST

Stable

View Details

Request Parameters

Request Body application/json

idstring

Required

API Pricing

$￥円 ₽

Model	Description	302.AI Price

cicada3.0	Create a language generation task	$0.001/second
Retrieve speech synthesis results	Retrieve speech synthesis results	Free
Create a voice customization task	Create a voice customization task	Free
Retrieve voice customization results	Retrieve voice customization results	Free
Delete customized voice	Delete customized voice	Free

cicada3.0

API Overview

API Console

API Reference (5)

Header Parameters

Request Body application/json

Header Parameters

Request Body application/json

Request Parameters Body

Header Parameters

Request Body application/json

Response Fields Description

Header Parameters

Query Parameters

Request Body application/json

API Pricing

cicada3.0

$0.001/second

Retrieve speech synthesis results

Free

Create a voice customization task

Free

Retrieve voice customization results

Free

Delete customized voice

Free

Recommended

Quick Access

Support

Legal Statement