Taisly Social Media Posting
taisly/agent
Free AI-first short-form video publishing to TikTok, Instagram Reels, YouTube Shorts, X, and Facebook from AI agents through Taisly.
Play a local audio file through the system's default speakers using Sonilo's MCP server.
Install Audio Playback
$ npx skills add sonilo-ai/skills --skill audio-playback -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sonilo-ai/skills audio-playback --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/sonilo-ai/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/audio-playback .claude/skills/audio-playback && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "audio-playback" agent skill from https://github.com/sonilo-ai/skills/tree/main/audio-playback into .claude/skills/audio-playback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio-playback", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/sonilo-ai/skills/tree/main/audio-playbackType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add sonilo-ai/skills --skill audio-playback -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sonilo-ai/skills audio-playback --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sonilo-ai/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/audio-playback .agents/skills/audio-playback && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "audio-playback" agent skill from https://github.com/sonilo-ai/skills/tree/main/audio-playback into .agents/skills/audio-playback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio-playback", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sonilo-ai/skills --skill audio-playback -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sonilo-ai/skills audio-playback --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sonilo-ai/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/audio-playback .cursor/skills/audio-playback && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "audio-playback" agent skill from https://github.com/sonilo-ai/skills/tree/main/audio-playback into .cursor/skills/audio-playback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio-playback", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/sonilo-ai/skills.git --path audio-playback--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add sonilo-ai/skills --skill audio-playback -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sonilo-ai/skills audio-playback --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sonilo-ai/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/audio-playback .gemini/skills/audio-playback && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "audio-playback" agent skill from https://github.com/sonilo-ai/skills/tree/main/audio-playback into .gemini/skills/audio-playback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio-playback", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install sonilo-ai/skills audio-playbackInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add sonilo-ai/skills --skill audio-playback -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sonilo-ai/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/audio-playback .github/skills/audio-playback && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "audio-playback" agent skill from https://github.com/sonilo-ai/skills/tree/main/audio-playback into .github/skills/audio-playback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio-playback", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sonilo-ai/skills --skill audio-playback -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sonilo-ai/skills audio-playback --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sonilo-ai/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/audio-playback .opencode/skills/audio-playback && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "audio-playback" agent skill from https://github.com/sonilo-ai/skills/tree/main/audio-playback into .opencode/skills/audio-playback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio-playback", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
audio-playback- GitHub stars
- 115
- Token cost
- ~813 tokens
- SKILL.md length
- 313 words
- Files
- 1
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- MIT
At a glance
Play a local audio file through the system's default speakers using Sonilo's MCP server.
- Wants to hear it immediately instead of just getting the saved path
- SKILL.md covers Quick Start, Tool, Parameters and Workflow Tips, plus 1 more section
- Calls brew and apt-get
- Tasks that involve MCP servers
What it does
Audio Playback is an agent skill from sonilo-ai/skills. Play a local audio file through the system's default speakers using Sonilo's MCP server. Use after generating a track with Sonilo (or for any local WAV/MP3/M4A/AAC/OGG/FLAC file) when the user wants to hear it immediately instead of just getting the saved path.
Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires the Sonilo MCP server connected — this is the one skill with no CLI equivalent, since playaudio exists only as an MCP tool. Does not require…
It sits in Media & Creative, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: Agent skills for Sonilo's licensed music, sound-effects, dubbing, and audio-ducking API. The licence is MIT.
When your agent uses it
- Wants to hear it immediately instead of just getting the saved path
- Tasks that involve MCP servers
Example prompts
- “s default speakers using Sonilo”
- “/audio-playback”
Requirements
- Python 3
- A credential in SONILO_API_KEY
- Compatibility (from SKILL.md): Requires the Sonilo MCP server connected — this is the one skill with no CLI equivalent, since `play_audio` exists only as an MCP tool. Does not require SONILO_API_KEY or network access — playback is entirely local. macOS and Linux use a native system player (afplay / mpg123 or aplay) when available; on Windows, and on Linux without a native player, this falls back to the sounddevice and soundfile Python packages plus PortAudio (brew install portaudio on macOS / apt-get install libportaudio2 on Debian-Ubuntu).
- Pre-approved tools (allowed-tools): Bash, Read, mcp__sonilo__*
What it can do on your machine
Read from SKILL.md and the folder at commit 1ce1bd8. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
BashReadmcp__sonilo__*
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
brewapt-get
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
Requires the Sonilo MCP server connected — this is the one skill with no CLI equivalent, since `play_audio` exists only as an MCP tool. Does not require SONILO_API_KEY or network access — playback is entirely local. macOS and Linux use a native system player (afplay / mpg123 or aplay) when available; on Windows, and on Linux without a native player, this falls back to the sounddevice and soundfile Python packages plus PortAudio (brew install portaudio on macOS / apt-get install libportaudio2 on Debian-Ubuntu).
From compatibility in the SKILL.md frontmatter.
Context cost
Audio Playback loads about 813 tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 313 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteRuns commands with sudoSKILL.md:40
ely (`brew install portaudio` on macOS, `sudo apt-get install libportaudio2` on Debian/Ubuntu). Everything else in this - NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash, Read, mcp__sonilo__*
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from sonilo-ai/skills at commit 1ce1bd8, republished under its MIT licence (© sonilo-ai). 313 words, ~813 tokens.
Download SKILL.mdSave it as
.claude/skills/audio-playback/SKILL.md (or your agent's skills folder).- name
- audio-playback
- description
- Play a local audio file through the system's default speakers using Sonilo's MCP server. Use after generating a track with Sonilo (or for any local WAV/MP3/M4A/AAC/OGG/FLAC file) when the user wants to hear it immediately instead of just getting the saved path.
- allowed-tools
- Bash, Read, mcp__sonilo__*
- compatibility
- Requires the Sonilo MCP server connected — this is the one skill with no CLI equivalent, since `play_audio` exists only as an MCP tool. Does not require SONILO_API_KEY or network access — playback is entirely local. macOS and Linux use a native system player (afplay / mpg123 or aplay) when available; on Windows, and on Linux without a native player, this falls back to the sounddevice and soundfile Python packages plus PortAudio (brew install portaudio on macOS / apt-get install libportaudio2 on Debian-Ubuntu).
- license
- MIT
Sonilo Audio Playback
Play a local audio file out loud through the system's default output device. This is the one Sonilo tool that makes no network call — it's pure local playback, useful right after a generation so the user can hear the result without leaving the conversation.
Setup: just needs the Sonilo MCP server connected — no API key required (see setup-api-key if the server itself isn't connected yet).
Quick Start
MCP tool call
play_audio(input_file_path="~/Desktop/thunder.m4a")There is no REST, Python/JS SDK, or CLI equivalent — this is local-only playback specific to the MCP server, not a Sonilo API call at all. If you're integrating via the SDK or CLI instead of MCP, just play the saved file with whatever your own language/platform normally uses for local audio playback.
Tool
| Tool | Description |
|---|---|
play_audio(input_file_path) | Play a local audio file through the system's default speakers. |
Parameters
| Parameter | Type | Notes |
|---|---|---|
input_file_path | string | Absolute path, or relative to SONILO_MCP_BASE_PATH. Supports .wav/.mp3/.m4a/.aac/.ogg/.flac. |
Workflow Tips
- Natural follow-up after any generation tool. Once
text_to_music,text_to_sfx,video_to_music, etc. return a saved path, offer (or default, if the user's phrasing implies it — e.g. "play what you just made") to callplay_audioon that same path. - Platform playback path: macOS uses
afplay; Linux prefersmpg123for.mp3oraplayotherwise. Windows has no native-player branch at all and always falls back to thesounddevice/soundfilePython packages, same as Linux when neithermpg123noraplayis installed — that fallback needs the systemPortAudiolibrary installed separately (brew install portaudioon macOS,sudo apt-get install libportaudio2on Debian/Ubuntu). Everything else in this repo works without PortAudio. - Respects the same file-access confinement as every other tool: a path outside
SONILO_MCP_BASE_PATHis rejected unlessSONILO_MCP_ALLOW_ANY_PATH=trueis set.
Error Handling
Raises if the file doesn't exist, isn't a recognized audio format, is outside the confined base path, or if no player is available on the platform (with a message naming what's missing).
© sonilo-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in audio-playback of sonilo-ai/skills.
Open the folder on GitHubat commit 1ce1bd8
Compare with similar skills
Audio Playback next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Audio Playback this skillsonilo-ai/skills | 115 | — | ~813 | Automated safety check: Notes | MIT | |
| Taisly Social Media Postingtaisly/agent | 217 | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Clipmivo VideoBarneyD66/clipmivo-tools | 142 | — | ~945 | Automated safety check: Pass | MIT | |
| Final Cut ProDareDev256/fcp-mcp-server | 121 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Resolve Tighten Recordingsamuelgursky/davinci-resolve-mcp | 3.4k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Resolve Fusionsamuelgursky/davinci-resolve-mcp | 3.4k | — | ~428 | Automated safety check: Pass | MIT |
Similar skills
Clipmivo Video
BarneyD66/clipmivo-tools
Create and manage AI video tasks through ClipmivoAI using its MCP server, CLI or REST API.
Final Cut Pro
DareDev256/fcp-mcp-server
Edit Final Cut Pro timelines with natural language via FCPXML.
Resolve Tighten Recording
samuelgursky/davinci-resolve-mcp
Tightening one long single-take recording — talking-head, screencast, tutorial, podcast video — by removing dead air in the DaVinci Resolve MCP.
Resolve Fusion
samuelgursky/davinci-resolve-mcp
Fusion composition work in the DaVinci Resolve MCP. An agent skill from samuelgursky/davinci-resolve-mcp.
Wjs Voicedrop
jianshuo/claude-skills
VoiceDrop 的入口。所有能力都在 MCP 里（voicedrop.cn/mcp，44 个工具：文章读写与版本、文风与蒸馏、挖矿与重写、社区与投币、算力、分享/公众号/小红书、书架读书与写书修书）。本 skill 只做一件事——把你接上那个 MCP：用它的 login 工具做 6+4 手机配对登录拿到令牌，然后接进客户端。触发词："voicedrop"、"登录…
More from sonilo-ai/skills
All 13 skills in this repoText To Sfx
sonilo-ai/skills
Generate a sound effect from a text description using Sonilo — a UI chime, a whoosh, an impact, ambience, a stylized cue — when there is no video to match.
Video To Music
sonilo-ai/skills
Score a video with original music using Sonilo — the model watches the cut and matches pacing, motion, and emotion, returning either the audio or a new video with the score muxed in.
Account
sonilo-ai/skills
Check the Sonilo account's available services, rate limits, free-trial allowance, and usage/billing history.
Audio Ducking
sonilo-ai/skills
Duck a music bed under a voice track using Sonilo — automatically lowers the music wherever the voice speaks and lifts it back in the gaps.
Auto Dubbing
sonilo-ai/skills
Dub a video into one or more other languages using Sonilo, translating and re-voicing the speech into a new video per language.
Proofread
sonilo-ai/skills
Transcribe a video with Sonilo and translate the transcript into editable .srt files — one per target language, plus the detected source language — so the wording can be read and corrected before…
Related
Works with
Categories
Questions about Audio Playback
What does Audio Playback do?
Play a local audio file through the system's default speakers using Sonilo's MCP server. Audio Playback is an agent skill from sonilo-ai/skills. Play a local audio file through the system's default speakers using Sonilo's MCP server.
When should I use Audio Playback?
Audio Playback fits situations like: wants to hear it immediately instead of just getting the saved path; tasks that involve MCP servers.
How do I install Audio Playback in Claude Code?
Run `npx skills add sonilo-ai/skills --skill audio-playback -a claude-code`. Or copy the skill folder (audio-playback in sonilo-ai/skills) into .claude/skills/audio-playback in your project. Claude Code loads it when a task matches its description.
How do I install Audio Playback in Codex?
Run `npx skills add sonilo-ai/skills --skill audio-playback -a codex`. Or copy the skill folder (audio-playback in sonilo-ai/skills) into .agents/skills/audio-playback in your project. Codex loads it when a task matches its description.
Can I use Audio Playback in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sonilo-ai/skills --skill audio-playback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audio-playback, .gemini/skills/audio-playback, .github/skills/audio-playback and .opencode/skills/audio-playback in your project.
What does Audio Playback need to run?
Going by SKILL.md and its folder, Audio Playback needs the command-line tools its instructions call (brew and apt-get). Our summary lists: Python 3; A credential in SONILO_API_KEY. Its frontmatter pre-approves these tools: Bash, Read, mcp__sonilo__*. Compatibility (from SKILL.md): Requires the Sonilo MCP server connected — this is the one skill with no CLI equivalent, since `play_audio` exists only as an MCP tool. Does not require SONILO_API_KEY or network access — playback is entirely local. macOS and Linux use a native system player (afplay / mpg123 or aplay) when available; on Windows, and on Linux without a native player, this falls back to the sounddevice and soundfile Python packages plus PortAudio (brew install portaudio on macOS / apt-get install libportaudio2 on Debian-Ubuntu)..
Does Audio Playback access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Audio Playback safe to install?
Our automated static check of SKILL.md found notes only (runs commands with sudo; pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Audio Playback use?
Audio Playback is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Audio Playback use?
About 813 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Audio Playback?
Skills that share tags, products or a category with Audio Playback: Taisly Social Media Posting (taisly/agent, 217 stars), Clipmivo Video (BarneyD66/clipmivo-tools, 142 stars), Final Cut Pro (DareDev256/fcp-mcp-server, 121 stars) and Resolve Tighten Recording (samuelgursky/davinci-resolve-mcp, 3.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Audio Playback?
sonilo-ai (a GitHub organization) maintains it in sonilo-ai/skills, which has 115 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 9, 2026.
Source: sonilo-ai/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.