Milystudio transcribe media
Skill Mily-Labs/agent-skills/plugins/milystudio-studio/skills/milystudio-transcribe-media
Transcribe and align speech in MilyStudio with local engines. Use for transcripts, word timing, diarization, searchable dialogue, or subtitle preparation.From its SKILL.md
npx -y skills add Mily-Labs/agent-skills --skill milystudio-transcribe-mediaAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.2 KB, 192 tokens by cl100k_base, as published. Nobody here has run it
milystudio-transcribe-media
Operate through the MilyStudio project, action, and job interfaces. Inspect capabilities before choosing commands because editor features may vary by installed release.
Workflow
- Inspect audio quality, languages, speakers, duration, and available local engines.
- Choose model, language, diarization, and alignment settings without sending media to a cloud by default.
- Run a cancellable transcription job and retain engine/version metadata.
- Review low-confidence regions, speaker changes, word timing, and source sync.
Guardrails
- Never edit project JSON, the UI store, or generated manifests directly when a typed action exists.
- Keep original media read-only and write only inside the active project artifact directories.
- Use dry-run before mutation, include the expected project revision, and stop on conflicts.
- Record assumptions, action IDs, job IDs, resulting revision, validation evidence, and unresolved risks.
What ships with it: 1 file
208 B alongside SKILL.md
agents/
- openai.yaml208 B