Transcribe spoken recordings into structured Markdown articles with frontmatter.
npx skills add https://github.com/kaiye/skills --skill voice-article
Please help me install this Agent Skill. Skill: voice-article Source: https://github.com/kaiye/skills/tree/main/voice-article Command: npx skills add https://github.com/kaiye/skills --skill voice-article
The Skill streamlines the process of transforming spoken recordings into organized, structured Markdown articles, reducing manual transcription and editing effort.
Send a voice recording and instruct the AI to generate a Markdown article with a cover image, then review and refine the draft.
High-intent search queries and answers about installing and using this skill.
To convert speech recordings into structured Markdown articles, submit your voice recording to the Skill. It handles speech-to-text transcription, outline structuring, and frontmatter generation to produce review-ready Markdown manuscripts for publishing workflows.
Yes, you can review and annotate a Markdown draft using screenshots. The Skill enables content review and optimization through annotated screenshots, facilitating targeted edits and iterative improvement for content creators and editors.
The best way to transcribe voice into a Markdown manuscript with frontmatter is using this Skill. It transforms spoken recordings into organized Markdown articles suitable for publishing, handling transcription, outline structuring, and review annotation automatically.
Yes, you need speech recognition and document formatting libraries to generate articles from voice recordings. The Skill depends on these libraries to handle speech-to-text transcription and produce structured, review-ready Markdown content for publishing.
To add a cover image and refine titles for a transcribed article, instruct the AI to generate a Markdown article after sending your voice recording. You can then review and iteratively refine the draft titles and cover within the workflow.
lvhuanidTranscribe spoken audio into written text using the z-ai-web-dev-sdk.
flowing-abyssApply %%instructions%% and rewrite ==highlighted== passages in annotated text.
ARCASSystemsAdd voice recognition and text-to-speech interaction to Founder OS.
e2662020Convert spoken audio in WAV and MP3 formats into written text transcriptions.
