agentleFS
full-aigc-skillsfull-aigc-skills/dreamina-skills/skills/dreamina-canvas-cli-text2voice/SKILL.md

dreamina-canvas-cli-text2voice

Skill4 starsChanged 58 days agoApache-2.0View on GitHub

当用户要求即梦画布文本转语音、朗读或全能配音(选音色或参考素材)时使用;仅负责 tts 模式的输入、参数校验、草稿与场景验收,公共画布素材、付费运行和恢复由 dreamina-canvas-cli 维护。

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never persist tokens, cookies or signed URLs;恢复只保留非敏感身份。

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

即梦画布文本转语音

When to use

仅处理 文本转语音(tts)。输入:逐字确认的朗读文本;通过 voice list 选择 --voice-name;legacy 形态不传 --model 和 --count。公开版 1.0.3 起,带 --scenario 的场景形态(text-reading 朗读、omni-dubbing 全能配音)允许并要求显式 --model,全能配音可选一个音色或改用 --ref 参考音频。

操作契约

项目标准
输入与前置用户确认的提示词、当前模型规格、projectId 及模式所需参考
副作用不带 --run 的节点写入保存草稿;付费执行走公共 execution 操作
输出交接返回的 nodeId 与 projectId;生成后另附 submitId 和校验后的资源
恢复规则恢复使用原 submitId;只有明确 absent + resubmittable 才按原身份恢复提交

Workflow

Step 1:复用 dreamina-canvas-cli 的公共调用契约和已确认 projectId;缺少安装或登录时按名称交给 setup/auth 技能。

Step 2:从当前模型/音色查询结果校验模式参数,读取 参数规范。不套用旧 CLI 的 model_version、resolution_type 或 poll。

Step 3:保存草稿,记录返回的 nodeId;修改已有节点时先读取当前状态,完整替换生成参数和引用,元数据才是稀疏更新。

# legacy:音色驱动,不传模型
dreamina-canvas --format json node create audio --project-id <projectId> \
  --prompt "<narration>" --mode tts --voice-name <voice-name>

# 全能配音(公开版 1.0.3 起):显式模型 + 场景,可选音色或参考素材
dreamina-canvas --format json node create audio --project-id <projectId> \
  --prompt "<dubbing script>" --mode tts \
  --model <scenario-capable-model> --scenario omni-dubbing \
  --voice-name <optional-voice> --ref "node:<audioNodeId>"

Step 4:需要生成时交给 dreamina-canvas-cli 的 execution 操作:node quote → node confirm → node run。提交前记录稳定 submitId;任务技能不自行批准预算。

Step 5:交给同一公共技能查询恢复与下载校验,核对本模式的实际产物。超时不换 submitId 重提。

Rules

  • 占位参数必须替换为当前 CLI 返回或用户确认的值;草稿命令不加 --run。
  • 不混用其他模式的必填项,批量上限从模型能力查询。
  • Never persist tokens, cookies or signed URLs;恢复只保留非敏感身份。
  • 缺少配套技能时安装:npx skills add full-aigc-skills/dreamina-skills --skill <skill-name>。

Progressive disclosure(按需读取)

  • 需要逐 flag 的必填/取值/冲突规则时,读取 参数规范。
  • 需要从当前 discovery 结果选模型、比例、分辨率或时长时,读取 模型或音色选择。
  • 需要批量、异步、多项目、迭代等成段工作流时,读取 常用场景组合。
  • 遇到超时、部分成功或恢复场景时,读取 异常处理。
  • 交付前自检时,读取 验收清单。
  • 首次运行看 成功场景;批量/异步/多项目/拒绝越权/失败恢复样例见 examples/ 目录。

Validation checklist

  • 输入与 tts 模式一致,参数经过实时发现。
  • 返回的 projectId、nodeId 与 submitId 正确交接,不能将受理视为完成。
  • 输出终态成功,下载后校验媒体类型、字节数和 SHA-256。

Gotchas

  • 节点生成编辑是 full replace,不能丢失原有引用。
  • 登录状态、计费权限与生成成功是不同检查。
  • 只生成用户要求的数量,不自动追加尝试。

不适用与边界

不适用于音乐生成或语音转文字。音乐使用 text2audio;输入文本未经确认时不改写旁白,不凭印象选择或承诺某个音色。

只读取当前操作必要的账户与素材信息;不存储、记录或输出访问令牌、cookie 和临时签名链接。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.