SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillschanjing-tts-voice-clone

chanjing-tts-voice-clone

Agents & models

View repository

Updated 10-15 20:11

About this skill

Chanjing TTS Voice Clone

Function Description

Based on the user-providedpublic reference audio URL(fetched by the Chanjing server), create a voice and synthesize speech; poll the task and download the result from the URL returned by the API. The scriptdoes notdepend on ffmpeg/ffprobe. For credentials, token write-back, and permissions, see manifest.yaml；access_token / expire_in When refreshing, fields in the same file will be overwritten, do not commit credentials to the version control repository.

Runtime Dependencies

  • python3 and in the same repository scripts/*.py
  • no ffmpeg/ffprobe gating

Environment Variables and Machine-Readable Declarations

  • Environment variable keys and descriptions:manifest.yaml（environment section) and this document
  • Variables, credentials,permissions.userContent(including the public reference audio URL fetched by Chanjing):manifest.yaml

Usage Commands

  • ClawHub(slug is subject to the registry):clawhub run chanjing-tts-voice-clone
  • This repository：python skills/chanjing-tts-voice-clone/scripts/create_voice.py …(see main text How to Use）

Registration and Review (Single Source of Truth)

Primary credentials,expire_in write-back and overwrite behavior, user reference audio URL boundaries, etc.:subject to manifest.yaml as authoritative. This article How to Use starts with the API steps and English interface descriptions.

When to Use This Skill

Use this skill when the user needs to generate speech from text, with a user-provided reference voice. The reference audio needs to be provided as a publicly accessible url.

This TTS service supports:

  • bilingual Chinese and English
  • adjustment of speech rate
  • sentence-level timestamp

How to Use This Skill

Prerequisites (Permission Verification): Before executing this Skill, you must first pass chanjing-credentials-guard to complete AK/SK and Token verification. The script and guard use the same set of credentials; when there are no credentials, it will execute open_login_page.py to open the registration/login page. For credentials and review cross-reference, see manifest.yaml。

Security & credentials (reference)

Purpose / Credentials / user-supplied reference URL / downloads: see manifest.yaml in credentials and clientPermissions(and compliance permissions); do not duplicate the maintenance table with the API documentation below this section.

Chanjing-TTS-Voice-Clone provides an asynchronous speech synthesis API. Hostname for all APIs is: "https://open-api.chanjing.cc". All requests communicate using json. You should use utf-8 to encode and decode text throughout this task.

  1. Obtain an access_token, which is required for subsequent requests
  2. Call the Create Voice API, which accepts a url to an audio file as reference voice
  3. Poll the Query Voice API until the result is success; keep the voice ID
  4. Call the Create Speech Generation Task API, using the voice ID, record the task_id
  5. Poll the Query Speech Generation Task Status API until the result is success
  6. When the task status is complete, use the corresponding url in API response to download the generated audio file

Get Access Token API

From ~/.chanjing/credentials.json read app_id and secret_key, if there is no valid Token then call:

POST /open/v1/access_token
Content-Type: application/json

Request body (using the locally configured app_id, secret_key):

{
  "app_id": "<从 credentials.json 读取>",
  "secret_key": "<从 credentials.json 读取>"
}

Response example:

{
  "trace_id": "8ff3fcd57b33566048ef28568c6cee96",
  "code": 0,
  "msg": "success",
  "data": {
    "access_token": "1208CuZcV1Vlzj8MxqbO0kd1Wcl4yxwoHl6pYIzvAGoP3DpwmCCa73zmgR5NCrNu",
    "expire_in": 1721289220
  }
}

Response field description:

First-level Field Second-level Field Description
code Response status code
msg Response message
data Response data
access_token Valid for one day, previous token will be invalidated
expire_in Token expiration time

Response status code description:

code Description
0 Success
400 Parameter format error
40000 Parameter error
50000 System internal error

Create Voice API

Post to the following endpoint to create a voice.

POST /open/v1/create_customised_audio
access_token: {{access_token}}
Content-Type: application/json

Request body example:

{
  "name": "example",
  "url": "https://example.com/abc.mp3"
}

Request field description:

Field Type Required Description
name string Yes A name for this voice
url string Yes url to the reference audio file, format must be one of mp3, wav or m4a. Supported mime: audio/x-wav, audio/mpeg, audio/m4a, video/mp4. Size must not exceed 100MB. Recommended audio length: 30s-5min
model_type string Yes Use "Cicada3.0-turbo"
language string No Either "cn" or "en", default to "cn"

Response example:

{
  "trace_id": "2f0f50951d0bae0a3be3569097305424",
  "code": 0,
  "msg": "success",
  "data": "C-Audio-53e4e53ba1bc40de91ffaa74f20470fc"
}

Response field description:

Field Description
code Status Code
msg Message
data Voice ID, to be used in following steps

Response status code description:

Code Description
0 Success
400 Parameter Format Error
10400 AccessToken Error
40000 Parameter Error
40001 QPS Exceeded
50000 Internal System Error

Poll Voice API

Send a GET request to the following endpoint to query whether the voice is ready to be used, voice ID is obtained in the previous step. The polling process may take a few minutes, keep polling until the status indicates the voice is ready.

GET /open/v1/customised_audio?id={{voice_id}}
access_token: {{access_token}}

Response example:

{
  "trace_id": "7994cedae0f068d1e9e4f4abdf99215b",
  "code": 0,
  "msg": "success",
  "data": {
    "id": "C-Audio-53e4e53ba1bc40de91ffaa74f20470fc",
    "name": "声音克隆",
    "type": "cicada1.0",
    "progress": 0,
    "audio_path": "",
    "err_msg": "不支持的音频格式，请阅读接口文档",
    "status": 2
  }
}

Response field description:

First-level Field Second-level Field Description
code Status Code
msg Response Message
data
id Voice ID
progress Progress: range 0-100
type
name
err_msg Error Message
audio_path
status 0-queued; 1-in progress; 2-done; 3-expired; 4-failed; 99-deleted

Response status code description:

Code Description
0 Success
10400 AccessToken Error
40000 Parameter Error
40001 QPS Exceeded
50000 Internal System Error

Create Speech Generation Task API

Post to the following endpoint to submit a speech generation task:

POST /open/v1/create_audio_task
access_token: {{access_token}}
Content-Type: application/json

Request body example:

{
  "audio_man": "C-Audio-53e4e53ba1bc40de91ffaa74f20470fc",
  "speed": 1,
  "pitch": 1,
  "text": {
    "text": "Hello, I am your AI assistant."
  }
}

Request field description:

Parameter Name Type Nested Key Required Example Description
audio_man string Yes C-Audio-53e4e53ba1bc40de91ffaa74f20470fc Voice ID, obtained from previous step
speed number Yes 1 Speech rate, range: 0.5 (slow) to 2 (fast)
pitch number Yes 1 Pitch (always set to 1)
text object text Yes Hello, I am your Cicada digital human Rich text, text length limit less than 4,000 characters
aigc_watermark bool No false Whether to add visible watermark to audio, default is false

Response field description:

Field Description
code Response status code
msg Response message
task_id Speech synthesis task ID

Example Response

{
  "trace_id": "dd09f123a25b43cf2119a2449daea6de",
  "code": 0,
  "msg": "success",
  "data": {
    "task_id": "88f635dd9b8e4a898abb9d4679e0edc8"
  }
}

Response status code description:

code Description
0 Success
400 Incoming parameter format error
10400 AccessToken verification failed
40000 Parameter error
40001 Exceeds QPS limit
40002 Production duration reached limit
50000 System internal error

Query Speech Generation Task Status API

Post a request to the following endpoint:

POST /open/v1/audio_task_state
access_token: {{access_token}}
Content-Type: application/json

Request body example:

{
  "task_id": "88f635dd9b8e4a898abb9d4679e0edc8"
}

Request field description:

Parameter Name Type Required Example Description
task_id string Yes 88f789dd9b8e4a121abb9d4679e0edc8 Task ID obtained in previous step

Response body example:

{
  "trace_id": "ab18b14574bbcc31df864099d474080e",
  "code": 0,
  "msg": "success",
  "data": {
    "id": "9546a0fb1f0a4ae3b5c7489b77e4a94d",
    "type": "tts",
    "status": 9,
    "text": [
      "猫在跌落时能够在空中调整身体，通常能够四脚着地，这种”猫右自己“反射显示了它们惊人的身体协调能力和灵活性。核磁共振成像技术通过利用人体细胞中氢原子的磁性来生成详细的内部图像，为医学诊断提供了重要工具。"
    ],
    "full": {
      "url": "https://cy-cds-test-innovation.cds8.cn/chanjing/res/upload/tts/2025-04-08/093a59021d85a72d28a491f21820ece4.wav",
      "path": "093a59013d85a72d28a491f21820ece4.wav",
      "duration": 18.81
    },
    "slice": null,
    "errMsg": "",
    "errReason": "",
    "subtitles": [
      {
        "key": "20c53ff8cce9831a8d9c347263a400a54d72be15",
        "start_time": 0,
        "end_time": 2.77,
        "subtitle": "猫在跌落时能够在空中调整身体"
      },
      {
        "key": "e19f481b6cd2219225fa4ff67836448e054b2271",
        "start_time": 2.77,
        "end_time": 4.49,
        "subtitle": "通常能够四脚着地"
      },
      {
        "key": "140beae4046bd7a99fbe4706295c19aedfeeb843",
        "start_time": 4.49,
        "end_time": 5.73,
        "subtitle": "这种，猫右自己"
      },
      {
        "key": "e851881271876ab5a90f4be754fde2dc6b5498fd",
        "start_time": 5.73,
        "end_time": 7.97,
        "subtitle": "反射显示了它们惊人的身体"
      },
      {
        "key": "fbb0b4138bad189b9fc02669fe1f95116e9991b4",
        "start_time": 7.97,
        "end_time": 9.45,
        "subtitle": "协调能力和灵活性"
      },
      {
        "key": "f73404d135feaf84dd8fbea13af32eac847ac26d",
        "start_time": 9.45,
        "end_time": 12.49,
        "subtitle": "核磁共振成像技术通过利用人体"
      },
      {
        "key": "e18827931223962e477b14b2b8046947039ac222",
        "start_time": 12.49,
        "end_time": 14.77,
        "subtitle": "细胞中氢原子的磁性来生成"
      },
      {
        "key": "d137bf2b0c8b7a39e3f6753b7cf5d92bd877d2d9",
        "start_time": 14.77,
        "end_time": 15.97,
        "subtitle": "详细的内部图像"
      },
      {
        "key": "0773911ae0dbaa763a64352abdb6bdac3ff8f149",
        "start_time": 15.97,
        "end_time": 18.41,
        "subtitle": "为医学诊断提供了重要工具"
      }
    ]
  }
}

Response field description:

First-level Field Second-level Field Third-level Field Description
code Response status code
msg Response message
data id Audio ID
type Speech type
status Status: 1 - in progress, 9 - done
text Speech text
full url url to download generated audio file
path
duration Audio duration
slice
errMsg Error message
errReason Error reason
subtitles(array type) key Subtitle ID
start_time Subtitle start time point
end_time Subtitle end time point
subtitle Subtitle text

Response field description:

Code Description
0 Response successful
10400 AccessToken verification failed
40000 Parameter error
50000 System internal error

Scripts

This Skill provides scripts (skills/chanjing-tts-voice-clone/scripts/), which use the same configuration file as chanjing-credentials-guard ; when there is no AK/SK, it willexecute the open_login_page.py scriptto open the registration/login page.

Script Description
create_voice.py Submit a custom voice task (reference audio URL), output voice_id
poll_voice.py Poll the custom voice until ready (status=2), output voice_id
create_task.py Create a TTS task using the custom voice, output task_id
poll_task.py Poll the TTS task until complete, output the audio download URL

Example (execute in the project root or skill directory):

# 1. 创建定制声音（参考音频需为公开 URL）
VOICE_ID=$(python skills/chanjing-tts-voice-clone/scripts/create_voice.py --name "我的声音" --url "https://example.com/ref.mp3")

# 2. 轮询直到声音就绪
python skills/chanjing-tts-voice-clone/scripts/poll_voice.py --voice-id "$VOICE_ID"

# 3. 创建 TTS 任务
TASK_ID=$(python skills/chanjing-tts-voice-clone/scripts/create_task.py --audio-man "$VOICE_ID" --text "Hello, I am your AI assistant.")

# 4. 轮询到完成，得到音频下载链接
python skills/chanjing-tts-voice-clone/scripts/poll_task.py --task-id "$TASK_ID"