Audio Transcription

Turns audio files into text using hosted Whisper models, with optional timestamps for subtitle work. You get durable artifacts, async job handling, and a choice between quality (standard) and speed (turbo). The skill manages the whole flow: request submission, polling, downloading results, and organizing everything under `.postplus/audio-transcription`. It hands off cleanly to subtitle-packager if you need SRT or ASS output. The execution boundary is clear and the CLI stops on real errors instead of guessing, which honestly feels rare and good. Best for speech-to-text jobs where you need persistence and timing data, not quick throwaway transcripts.

skills.sh installs: 1.3K
GitHub stars: 27
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add postplusai/postplus-skills --skill audio-transcription --agent claude-code

Installs into .claude/skills of the current project.

Files

Audio Transcription

Use When

The input is audio and the main job is speech-to-text, subtitle-ready timing, rough speech search, multilingual transcription, or durable transcript artifacts.
Use video-transcription for video inputs and media-analysis for semantic video understanding.

If a timed transcript already exists and only subtitle output is requested, skip transcription and read the local subtitle conversion reference.

Do Not Use When

The task needs new creative generation or visual analysis rather than speech or subtitles.
Required inputs are missing and guessing would change the result.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly