Voice Clone

What it does

When your agent uses it

• Tasks that involve Text to speech and voice

Example prompts

• “声音克隆、克隆/复刻我的声音、用我的声音配音、定制专属音色”
• “/voice-clone”

Requirements

• Python 3
• A credential in DASHSCOPE_API_KEY
• A credential in MINIMAX_API_KEY

Workflow steps

2 steps, taken from the step headings in SKILL.md.

1. 1登记音色（enroll，得到 voice_id）
2. 2合成（clone）

What it can do on your machine

Read from SKILL.md and the folder at commit 278f420. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • DASHSCOPE_API_KEY
  • MINIMAX_API_KEY
  • FISH_API_KEY
  • VOICE_API_KEY
  • GEMINI_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Voice Clone loads about 715 tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 175 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~32

When it runs · the whole SKILL.md, loaded when a task matches

~715

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:17

  ` 到 `AGENTS.md` 末尾给出的 Easel 项目根，确认当前目录有 `.env` 和 `skills/shared/scripts/`，再运行注册表、`check`、`enroll` 或 `clone`。不得改用 workspa

• NoteMentions a .env fileSKILL.md:19

  选 provider 并在 `.env` 填 key，再 `check` 离线校验：

• NoteMentions a .env fileSKILL.md:21

  e.py check --provider minimax --env-file .env

• NoteMentions a .env fileSKILL.md:24

  | provider | 服务 | .env 需配 |

• NoteMentions a .env fileSKILL.md:34

  y.py configured --group voice --env-file .env`。只有一个可用时显式选择；多个可用且用户没点名时，列出 provider/模型询问本次使用哪个，不按 `VOICE_PROVIDER` 擅自选择。

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ZJU-REAL/Easel at commit 278f420, republished under its Apache-2.0 licence (© ZJU-REAL). 175 words, ~715 tokens.

name

voice-clone

description

上传本人语音样本克隆专属音色，再用它合成口播、旁白或带货语音。当用户说“声音克隆、克隆/复刻我的声音、用我的声音配音、定制专属音色”时使用，需要用户自备云端 provider 凭证。使用公共现成音色时改用 tts-voiceover。

layer

produce

python skills/shared/scripts/voice_clone.py check --provider minimax --env-file .env

# minimax：上传样本文件
python skills/shared/scripts/voice_clone.py enroll --provider minimax \
  --sample me.mp3 --name my_voice
# dashscope：用公网可访问的样本 URL
python skills/shared/scripts/voice_clone.py enroll --provider dashscope \
  --sample-url https://.../me.wav --name myv

python skills/shared/scripts/voice_clone.py clone --provider minimax \
  --voice-id my_voice --text "大家好，欢迎来到我的频道" --speed 1.0 \
  -o outputs/主题名/vo.mp3

© ZJU-REAL, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/openclaw/voice-clone of ZJU-REAL/Easel.

Open the folder on GitHubat commit 278f420