
Chanjing Tts Voice Clone
This lets Claude synthesize speech using Chanjing's TTS API with voice cloning from a reference audio file you provide via public URL. The flow is async: you submit a reference audio URL (mp3, wav, or m4a), wait for the voice profile to build, then generate speech from text using that cloned voice. Supports bilingual Chinese and English with adjustable speech rate and sentence timestamps. You'll need Chanjing credentials (app_id and secret_key), and the skill handles token refresh automatically by writing back to the same credentials file. The reference audio gets fetched by Chanjing's servers, so it needs to be publicly accessible. Polling can take a few minutes while the voice processes, but no local ffmpeg required since everything happens server-side.
- skills.sh installs
- 212
- GitHub stars
- 22
- last updated
- Aug 21, 2026
Install
$ npx -y skills add chanjing-ai/chan-skills --skill chanjing-tts-voice-clone --agent claude-codeInstalls into .claude/skills of the current project.
Files
Chanjing TTS Voice Clone
功能说明
基于用户提供的参考音频公网 URL(由蝉镜服务端拉取)创建音色并合成语音;轮询任务并从接口返回 URL 下载结果。脚本不依赖 ffmpeg/ffprobe。凭据、令牌写回与权限见 manifest.yaml;access_token / expire_in 刷新时会覆盖同文件字段,勿将凭证提交版本库。
运行依赖
- python3 与同仓库
scripts/*.py - 无 ffmpeg/ffprobe 门控
环境变量与机器可读声明
- 环境变量键名与说明:
manifest.yaml(environment段)及本文 - 变量、凭据、
permissions.userContent(含参考音公网 URL 由蝉镜拉取):manifest.yaml
使用命令
- ClawHub(slug 以注册表为准):
clawhub run chanjing-tts-voice-clone - 本仓库:
python skills/chanjing-tts-voice-clone/scripts/create_voice.py …(见正文 How to Use)
登记与审稿(单一事实来源)
主凭据、expire_in 写回与覆盖行为、用户参考音 URL 边界等:以 manifest.yaml 为准。本篇 How to Use 起为 API 步骤与英文接口说明。
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
Sponsors
Details
- Repository
- github.com/chanjing-ai/chan-skills
- Categories
- Backend & APIs, Generative Media
- First seen
- Jun 3, 2026