7 synchronicity-labs

translate-and-dub Skill

使用 sync. labs(sync.so)将一个源视频的语音翻译成其他语言,并将说话人的口型与配音重新同步。支持本地文件、URL 或 YouTube、TikTok、Instagram、Facebook 链接,可输出一种或多种语言。适用于"把这个视频配音成西班牙语""把我的 YouTube 视频翻译成日语"、AI 配音、视频翻译或一个视频的多语言版本。不适用于仅做字幕、翻译文本文档、对用户已有的音频做口型同步(lipsync),或跨市场的多视频本地化活动(localize-campaign)。

安装方式:把技能目录放入 ~/.claude/skills/(Claude Code)或在 claude.ai 设置中启用;也可复制右侧安装命令一键添加。

查看源码

技能指令原文(SKILL.md)

Translate and dub a video

sync. labs | Translation and dubbing guide

Delivers one dubbed MP4 per target language, with lips matched to the new audio. The dubbed voice follows the original speaker's.

If no sync. tools are available, follow references/connect.md first. Without the MCP tools, use dubParams on POST /v2/generate as shown in references/api.md.

Inputs

  • Video: a local file, a public URL, a sync. video asset ID, or a social link. It needs its original speech on the audio track.
  • Target languages: ask if none were given. Use sourceLang: "auto" unless the user names the spoken language.

Tools

| Step | Tool |
| --- | --- |
| Check languages | dubbing_get-options |
| Create the project | projects_create |
| Save the video | assets_upload, assets_create-upload-url + assets_create, or assets_create with a link |
| Quote | generations_estimate-cost |
| Create | dubbing_create, or jobs_create-many for 2 or more languages |
| Wait | generations_get, or jobs_get-many for a set |

Steps

  1. Languages. Call dubbing_get-options and check every requested language. For any that isn't supported, name the closest supported option.
  2. Project. Call projects_create with a new random UUID as id, a short name and defaultWorkflow: "translate_and_dub". Save the returned id as projectId. Pass it wherever a tool asks for projectId, and add projectIntent: "explicit" only on tools that take that field.
  3. Save the video into that project. Follow references/media-input.md.
  4. Quote. Call generations_estimate-cost with workflow: "translate-and-dub", model: "sync-3" and the video's length as duration in seconds. Show the returned estimate and its breakdown per language and in total. If it reports external provider charges as excluded, say they're extra.
  5. Confirm. Show the video, the languages and the estimate, and wait for approval. Skip the wait only if the user already approved this exact request and cost.
  6. Create. Each language is one dubbing_create with videoAssetId, targetLang, sourceLang, model: "sync-3", the projectId with projectIntent: "explicit", and its own new idempotencyKey, saved before the call.
  • One language: call dubbing_create once. If a response is lost, retry once with the same key and inputs.
  • 2 or more languages, with jobs_create-many listed: save a new UUID for the set, then call jobs_create-many once with tool: "dubbing_create", that UUID as idempotencyKey, and one item per language holding exactly those arguments. The one approval covers every language. If the response is unclear, send the identical call again. When it returns remaining, send remaining again exactly as returned once running languages finish; if the tool refuses a single remaining item, send that language with dubbing_create and the same key. A failed item with a 5xx or no status may still have started, so send it again with the same keys.
  • 2 or more languages without it: call dubbing_create once per language, as for one language.
  1. Wait and deliver. Poll generations_get with each id and wait: true until each is final, or pass the set's jobs to jobs_get-many with wait: true and call it again while some are still running. Dubbing takes longer than plain lipsync, so tell the user it may take several minutes. Give each exact outputMediaUrl, unchanged and labelled with its language.

Rules

  • One paid job per language. Never resubmit a language to check progress.
  • Several source videos across languages or markets is a campaign: hand it to the localize-campaign skill, which plans the matrix and pilots one version first.
  • If one language fails, report it and keep the others.
  • Text on screen isn't translated, and the output is dubbed video only. Don't offer subtitles or a translated transcript as a substitute.
  • If dubbing fails with a voice-provider error and the user connected their own ElevenLabs key to sync., the cause is usually that key's credits or validity. Say so.