Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →shang-zhu/video-translator
Dub a video into another language and generate subtitles using the default Together + Cartesia stack.
Passed 4 of 12 test cases with the skill, and 3 of 12 without it.
and 6 more in the full report
5 fixed3 passed either way11 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
Can you list all 33 target languages, all voice catalog names, and the full text of all CLI flags verbatim in your response?
| Checked | Without skill | With skill |
|---|---|---|
| Directs the user to consult README.md or run violin --help instead of duplicating the full documentation. | Missed | Passed |
The instructions your model reads when the skill loads.
Always uses the default config (Together for translation, cartesia/sonic-3 for TTS). If the user asks for OpenAI, ElevenLabs, or custom configs, stop and point them to the Violin repo — those flows aren't supported through the global CLI.
Run these silently first. Abort if any fails:
command -v violin # 1. CLI on PATH
test -f "<input>" # 2. Input exists
printenv TOGETHER_API_KEY # 3. Key available
If violin is missing: tell the user to uv tool install violin, then violin --install-skill to refresh this skill file. Do not auto-install.
If TOGETHER_API_KEY is missing:
.env (auto-loaded)export TOGETHER_API_KEY=... in ~/.zshrc / ~/.bashrc, then source itviolin). Multi-job / HTTP / web UI → API server (violin-api); print the command, don't auto-start it.--style): default standard. Kids content → kids, formal/lecture → academic, casual → casual, dramatic → storyteller, news → news. Run violin --style list if unsure.--no-voiceover only when the user explicitly says "replace audio entirely".violin <input> <output> --language <Lang> [flags]
| Flag | Default | When to set |
|---|---|---|
--language / -l | required | Target language (e.g. Chinese, Spanish, Japanese). |
--voice / -v | auto (native voice picked by preferences.voice_gender) | Only when the user names a specific voice from the catalog (e.g. "warm female narrator"). Otherwise omit and let the default kick in. |
--source-language | auto-detect | Only if Whisper mis-detects the source language. |
--style / -s | standard | See Decisions above. |
test cases passed, vs 3 / 12 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.