audio-transcription — Claude Code skill: how to install and use
Transcribes local or web audio into text with timestamps via the PostPlus CLI and converts existing timed transcripts into SRT or ASS subtitles.
npx skills add PostPlusAI/postplus-skills --skill audio-transcription -a claude-codeWhat audio-transcription does
This skill guides the agent to process speech through the postplus media transcribe command. You can pass local sound files, HTTPS links, or data URIs into the --audio argument. The CLI handles jobs asynchronously, saving internal runs and manifests into .postplus/audio-transcription.
Supplying the file duration in --duration-seconds is mandatory. The CLI validates media duration beforehand, stopping execution immediately if the flag is omitted. Hosted transcription consumes PostPlus credits, so jobs pause whenever the account balance runs out.
Generating subtitle files like SRT or ASS from an existing transcript happens locally. You do not spend credits on another remote call just to change formats. For draft passes, the tool provides an economical variant alongside the default high-precision model.
What it helps with
- transcribe local audio tracks or remote URLs with exact timestamps
- convert existing timed transcripts to SRT or ASS subtitles locally
- run postplus doctor diagnostics to verify skill setup
- generate quick draft transcripts using the economical model variant
Example prompts for the agent
- Transcribe ./meeting.wav with duration-seconds set to 180 and keep timestamps
- Convert ./result.json into an SRT subtitle file locally
- Run postplus doctor --skill audio-transcription to verify my setup
How to install audio-transcription
1Skills CLI (Vercel)
npx skills add PostPlusAI/postplus-skills --skill audio-transcription -a claude-code2Manually: put the files in place
~/.claude/skills/audio-transcription/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/audio-transcription/
1Skills CLI (Vercel)
npx skills add PostPlusAI/postplus-skills --skill audio-transcription -a codex2Manually: put the files in place
.agents/skills/audio-transcription/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add PostPlusAI/postplus-skills --skill audio-transcription -a cursor2Manually: put the files in place
.cursor/skills/audio-transcription/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install PostPlusAI/postplus-skills audio-transcription2Manually: put the files in place
.github/skills/audio-transcription/SKILL.md1Skills CLI (Vercel)
npx skills add PostPlusAI/postplus-skills --skill audio-transcription -a gemini-cli2Platform CLI
gemini skills install https://github.com/PostPlusAI/postplus-skills --path skills/40-creative/audio-transcriptionManually: put the files in place
.devin/skills/audio-transcription/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add PostPlusAI/postplus-skills --skill audio-transcription -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about audio-transcription
How to install audio-transcription in Claude Code?
Run npx skills add PostPlusAI/postplus-skills --skill audio-transcription -a claude-code. The skill file will be placed in ~/.claude/skills/audio-transcription/SKILL.md.
What does the audio-transcription skill do?
It connects your coding assistant to the PostPlus CLI to generate speech transcripts with timestamps. It also creates SRT or ASS subtitles from saved results on your machine.
Does subtitle generation require a second transcription job?
No extra remote job is needed. Once a timed transcript exists, the skill builds SRT and ASS files locally without using more credits.
