with one click
advanced-dubbing-studio
Submit audio or video for multilingual dubbing, poll status, and download dubbed audio. Use when the user asks for dubbing, 多语言配音, 视频翻译配音, 译制片, or wants a source clip dubbed into another language.
Menu
Submit audio or video for multilingual dubbing, poll status, and download dubbed audio. Use when the user asks for dubbing, 多语言配音, 视频翻译配音, 译制片, or wants a source clip dubbed into another language.
Generate or edit a single image via OpenRouter (google/gemini-3.1-flash-image-preview by default). Accepts a text prompt and optional --input-image for image-to-image editing. Trigger when the user asks for an AI image, illustration, concept art, product render, or wants to modify an existing image.
Render a single 3-15s video clip via Seedance 2.0. Supports two backends: OpenRouter (default, model bytedance/seedance-2.0) and the official Volcengine ARK / BytePlus ModelArk endpoint (model doubao-seedance-2-0-260128 / dreamina-seedance-2-0-260128). Accepts a structured English video prompt, optional first-frame image, and optional identity/style reference image. Trigger when the user asks for AI video clip generation, 分镜视频, seedance, or wants a short cinematic shot from a prompt + frame.
Use this meta-skill instead of answering directly when the current user asks to draft, repair, compile, or produce an academic/research paper or LaTeX manuscript. It uses multi-skill orchestration for manuscript workflows that need source search, citation planning, experiment or figure/table placeholders, drafting, length checks, citation integrity, and LaTeX/PDF compilation. Ordinary paper requests use a compact draft path; explicit full/PDF/long-form requests use the full manuscript path. Do not use it for web research reports, slide decks, document decisions, or generic plotting.
Generate instrumental music, background beds, jingles, or sung songs with lyrics through OpenSquilla audio tools. Use when the user asks for BGM, music generation, 唱歌, 生成歌曲, lyrics to song, or a playable music audio artifact.
Create and register cloned voices for later TTS only when the speaker has explicit consent. Use when the user asks for voice clone, clone voice, 克隆音色, 复刻声音, or wants a reusable voice_id.
Convert a local source recording into an authorized target voice. Use when the user asks for voice conversion, voice changer, 换声, 变声, 音色转换, or converting existing narration to another approved voice.
| name | advanced-dubbing-studio |
| description | Submit audio or video for multilingual dubbing, poll status, and download dubbed audio. Use when the user asks for dubbing, 多语言配音, 视频翻译配音, 译制片, or wants a source clip dubbed into another language. |
| triggers | ["dubbing","dub this","多语言配音","视频配音","翻译配音","译制"] |
| provenance | {"origin":"opensquilla-original","license":"Apache-2.0","maintained_by":"OpenSquilla"} |
| metadata | {"opensquilla":{"risk":"high","capabilities":["network-read","filesystem-write"],"requires_tools":["dubbing_generate","dubbing_status","dubbing_download","audio_provider_capabilities"]}} |
Runs provider-backed dubbing for local audio/video assets. OpenRouter can help
translate, review style, or summarize job status, but the dubbing job itself
must use dubbing_generate, dubbing_status, and dubbing_download.
Before calling tools, extract these fields from the user request:
OpenRouter can help translate or adapt lines, but it is not an audio provider and cannot perform the dubbing job itself.
audio_provider_capabilities if dubbing availability is uncertain.dubbing_generate.dubbing_status or use dubbing_download with polling when
appropriate.For long videos, uncertain accents, or high-value assets, submit or prepare a short preview clip first when the workflow permits it. Use the preview to check translation style, target locale, speaker count, pacing, and whether the provider preserves speaker separation.
If only the full source file is available, explain that the first run may need one retry for locale/accent tuning and keep the target locale explicit in the job notes.
dubbing_generate returns status=ok, return the job ID and tell the
user whether download is pending or already being polled.dubbing_status is not ready, report the current status without claiming
failure.dubbing_download returns audio, put the playable artifact/path first.not_available or an error, quote the note and
distinguish provider setup, feature gating, key/quota limits, source format,
language support, and provider processing delay.When dubbing, the target language is not enough; choose the target locale and accent as well:
Chinese: prefer 普通话 / Mainland Mandarin target settings unless the user asks for Cantonese, Taiwanese Mandarin, Sichuan dialect, etc.
English: preserve en-US, en-GB, en-AU, en-IN, en-SG, or any locale named by the user.
Spanish: distinguish es-ES and Latin American variants such as es-MX.
Portuguese: distinguish pt-BR and pt-PT.
French: distinguish fr-FR and fr-CA when requested.
Japanese/Korean/German/Italian/etc.: use native target-language voices rather than English-accented fallback voices.
Keep translated lines natural in Chinese, not word-for-word English order.
Avoid unnecessary English names or romanization unless the original requires it.
If the result sounds like the wrong accent, retry with shorter translated lines, clearer punctuation, and a voice native to the target locale.
Return: