Listen to content

Skill zjczg/listen-to-content/skills/listen-to-content

Generate, cache, play, and control DashScope speech on macOS with Codex and OpenCode Skills.

Install

npx -y skills add zjczg/listen-to-content --skill listen-to-content

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

19 days oldThe repository was created 19 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
2 stars2 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.

What its author says it does

Copied from the file, not written here

Convert local text, Markdown, DOCX, or two-role podcast scripts into DashScope speech on macOS, then play, pause, resume, stop, inspect, clean, and preserve the generated audio. Use when the user asks an AI agent to read content aloud, review a podcast, control playback, manage temporary speech cache, estimate synthesis cost, or save an approved recording.

SKILL.md

1.8 KB, 314 tokens by cl100k_base, as published. Nobody here has run it

Listen To Content

Resolve the directory containing this loaded SKILL.md, then use its bundled launcher for every operation:

"<skill-directory>/scripts/listen" <command> [options]

Do not assume a Codex or OpenCode configuration path. Use the Skill location provided by the client.

Safety

Before the first uncached synthesis request, tell the user that the selected text will be sent to Alibaba Cloud DashScope and obtain explicit approval.
Add --confirm-cloud only after that approval.
Never print, copy, or persist an API key.
Generate a short preview before a long document unless the user explicitly asks for the complete recording.

Operations

Inspect without cloud access: synthesize --file "<path>" --dry-run
Generate and play: synthesize --file "<path>" --confirm-cloud --play
Short preview: add --max-segments 2
Existing audio: play "<path>"
Playback: pause, resume, stop, or status
Cache: list, info, or clean --dry-run
Final recording: pin --destination "<path>" --confirmed only after the user explicitly approves both the script and audio.

Markdown scripts with standalone [面试官] and [候选人] markers use separate voices. Temporary audio stays in the application cache and must not be added to the user's content repository.

Gives 0 of the 12 instructions most video audio skills give in 314 tokens

Counted across 622 of the 795 authors here whose files we hold, read 2026-08-07

read individual rule files for detailed explanationsin 21 of 622, across 10 files
render final videoin 13 of 622, across 6 files
Use WAV PCM 16kHz mono audio formatin 12 of 622, across 3 files
Use this skill when dealing with Remotion codein 11 of 622, across 4 files
save generated audio to a WAV filein 11 of 622, across 4 files
handle conversion errors gracefullyin 10 of 622, across 6 files
add captions to videos alwaysin 10 of 622, across 4 files
generate music from text descriptions using MusicGenin 9 of 622, across 2 files
do not skip pipeline layersin 9 of 622, across 3 files
do not make one tool do everythingin 9 of 622, across 3 files
use azure document intelligence for complex pdfsin 9 of 622, across 4 files
never ask the user to paste their full API keyin 9 of 622, across 3 files

Said here and by no other author read

use the bundled listen launcher script
obtain explicit user approval before cloud synthesis
add the confirm-cloud flag only after approval
generate a short preview before long documents
run synthesis with the dry-run flag first
use separate voices for marked two-role scripts

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.