← 返回 Skills 市场
neckr0ik

Audio Handler

作者 Neckr0ik · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
853
总下载
1
收藏
6
当前安装
1
版本数
在 OpenClaw 中安装
/install audio-handler
功能描述
Read, analyze, convert, trim, merge, adjust volume, and transcribe audio files in multiple formats including MP3, WAV, FLAC, AAC, OGG, and more.
使用说明 (SKILL.md)

Audio Handler

Analyze, convert, and process audio files.

Supported Formats

Format Extensions Read Convert Metadata
MP3 .mp3 ✅ ✅ ✅
WAV .wav ✅ ✅ ✅
FLAC .flac ✅ ✅ ✅
AAC/M4A .m4a, .aac ✅ ✅ ✅
OGG .ogg ✅ ✅ ✅
Opus .opus ✅ ✅ ✅
WMA .wma ✅ ✅ ✅
AIFF .aiff, .aif ✅ ✅ ✅

Quick Commands

Metadata (ffprobe)

# Get all metadata
ffprobe -v quiet -print_format json -show_format -show_streams audio.mp3

# Get duration only
ffprobe -v error -show_entries format=duration -of default=noprint_wrappers=1:nokey=1 audio.mp3

# Get bitrate
ffprobe -v error -show_entries format=bit_rate -of default=noprint_wrappers=1:nokey=1 audio.mp3

# Get sample rate and channels
ffprobe -v error -select_streams a:0 -show_entries stream=sample_rate,channels -of default=noprint_wrappers=1 audio.mp3

# Human-readable info
ffprobe -hide_banner audio.mp3

Convert Formats (ffmpeg)

# Convert to MP3 (good quality)
ffmpeg -i input.wav -codec:a libmp3lame -qscale:a 2 output.mp3

# Convert to MP3 (specific bitrate)
ffmpeg -i input.wav -codec:a libmp3lame -b:a 192k output.mp3

# Convert to WAV (uncompressed)
ffmpeg -i input.mp3 output.wav

# Convert to FLAC (lossless)
ffmpeg -i input.wav output.flac

# Convert to M4A/AAC
ffmpeg -i input.wav -codec:a aac -b:a 256k output.m4a

# Convert to OGG Vorbis
ffmpeg -i input.wav -codec:a libvorbis -qscale:a 5 output.ogg

# Convert to Opus (best for speech)
ffmpeg -i input.wav -codec:a libopus -b:a 64k output.opus

Trim & Clip

# Trim audio (from 30s to 90s)
ffmpeg -i input.mp3 -ss 30 -to 90 -c copy output.mp3

# Trim from start to duration
ffmpeg -i input.mp3 -t 60 -c copy output.mp3  # First 60 seconds

# Trim with re-encode (more accurate)
ffmpeg -i input.mp3 -ss 30 -to 90 output.mp3

Volume & Speed

# Adjust volume (2x louder)
ffmpeg -i input.mp3 -af "volume=2" output.mp3

# Reduce volume (half)
ffmpeg -i input.mp3 -af "volume=0.5" output.mp3

# Normalize audio
ffmpeg -i input.mp3 -af "loudnorm" output.mp3

# Speed up (1.5x)
ffmpeg -i input.mp3 -af "atempo=1.5" output.mp3

# Slow down (0.75x)
ffmpeg -i input.mp3 -af "atempo=0.75" output.mp3

Merge & Concatenate

# Concatenate audio files
ffmpeg -i "concat:part1.mp3|part2.mp3|part3.mp3" -acodec copy output.mp3

# Merge with file list
echo "file 'part1.mp3'" > list.txt
echo "file 'part2.mp3'" >> list.txt
ffmpeg -f concat -safe 0 -i list.txt -c copy output.mp3

# Mix two audio tracks
ffmpeg -i voice.mp3 -i music.mp3 -filter_complex amix=inputs=2:duration=longest output.mp3

Extract Audio from Video

# Extract audio track
ffmpeg -i video.mp4 -vn -acodec copy audio.aac

# Extract and convert
ffmpeg -i video.mp4 -vn -acodec libmp3lame -b:a 192k audio.mp3

Playback (macOS)

# Play audio file
afplay audio.mp3

# Play with volume (0.0 to 1.0)
afplay -v 0.5 audio.mp3

# Play in background
afplay audio.mp3 &

# Stop playback
killall afplay

Text-to-Speech (macOS)

# Speak text
say "Hello, this is a test"

# Save to file
say -o output.aiff "This will be saved as audio"

# List voices
say -v ?

# Use specific voice
say -v "Samantha" "Hello, I am Samantha"

# Convert to MP3
say -o temp.aiff "Text to convert" && ffmpeg -i temp.aiff output.mp3 && rm temp.aiff

Scripts

audio_info.sh

Get comprehensive audio metadata.

~/Dropbox/jarvis/skills/audio-handler/scripts/audio_info.sh \x3Caudio_file>

convert_audio.sh

Convert between formats with quality options.

~/Dropbox/jarvis/skills/audio-handler/scripts/convert_audio.sh \x3Cinput> \x3Coutput> [quality]

trim_audio.sh

Trim audio with start/end times.

~/Dropbox/jarvis/skills/audio-handler/scripts/trim_audio.sh \x3Cinput> \x3Coutput> \x3Cstart> \x3Cend>

normalize_audio.sh

Normalize volume level.

~/Dropbox/jarvis/skills/audio-handler/scripts/normalize_audio.sh \x3Cinput> \x3Coutput>

Quality Guide

Use Case Format Settings
Music archive FLAC -codec:a flac
Music portable MP3 -codec:a libmp3lame -qscale:a 2
Podcast/speech Opus -codec:a libopus -b:a 64k
Voice memo M4A -codec:a aac -b:a 128k
Uncompressed WAV -codec:a pcm_s16le

Notes

  • ffmpeg handles almost all audio formats
  • -c copy is fast but may be inaccurate for trimming
  • Re-encode (-af) for precise cuts but takes longer
  • Opus is best for speech at low bitrates
  • Use loudnorm filter for consistent volume across files
安全使用建议
This skill appears to do what it says: local audio processing using ffmpeg/ffprobe and simple bash scripts. Before installing: 1) Be aware the SKILL.md and scripts assume tools that are not declared — ensure you have ffmpeg and ffprobe installed (and jq if you want the JSON-parsing output); macOS-only commands (afplay, say) are optional. 2) Inspect the scripts and only run them on files you trust (ffmpeg processes can crash or be abused by malformed media). 3) The examples reference a ~/Dropbox/... path — update paths to your environment. 4) Because there's no install step, no network download occurs during install, but the scripts will execute binaries on your machine when invoked. If you need the skill to declare dependencies or to avoid execution on untrusted files, request the author to add required-binaries and clarify platform support.
功能分析
Type: OpenClaw Skill Name: audio-handler Version: 1.0.0 The audio-handler skill bundle provides standard utilities for processing audio files using ffmpeg, ffprobe, and macOS-specific tools like afplay and say. The included shell scripts (audio_info.sh, convert_audio.sh, etc.) perform legitimate metadata extraction, format conversion, normalization, and trimming without any signs of data exfiltration, malicious execution, or prompt injection.
能力评估
ℹ Purpose & Capability
The name/description (audio analysis, convert, trim, normalize, transcribe) match the provided scripts and ffmpeg/ffprobe commands. However, the skill declares no required binaries while the SKILL.md and scripts clearly rely on external tools (ffmpeg, ffprobe, jq, and on macOS afplay/say). This is a documentation/packaging omission but not evidence of malicious intent.
✓ Instruction Scope
Runtime instructions and included scripts operate only on local files and use standard audio tooling; they do not reference external endpoints, collect unrelated system data, or read environment variables or configuration outside the skill. The examples do reference a user-home path (~/Dropbox/jarvis/...) which is only an example and may not exist on a target system.
✓ Install Mechanism
There is no install spec (instruction-only with included scripts), so nothing will be downloaded during install. Scripts are plain bash with no obfuscation or remote fetches. This is a low-risk install footprint.
✓ Credentials
The skill requests no credentials, env vars, or config paths. That is proportionate to its stated purpose. Note: it implicitly requires command-line tools (ffmpeg/ffprobe/jq; macOS afplay/say) which are not declared under 'required binaries'.
✓ Persistence & Privilege
always is false and the skill does not request any elevated or persistent platform privileges. It does not modify other skills or system-wide agent settings.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install audio-handler
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /audio-handler 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release - extract metadata, convert, trim, normalize audio (MP3, WAV, FLAC, M4A, OGG, Opus)
元数据
Slug audio-handler
版本 1.0.0
许可证 —
累计安装 6
当前安装数 6
历史版本数 1
常见问题

Audio Handler 是什么？

Read, analyze, convert, trim, merge, adjust volume, and transcribe audio files in multiple formats including MP3, WAV, FLAC, AAC, OGG, and more. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 853 次。

如何安装 Audio Handler？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install audio-handler」即可一键安装，无需额外配置。

Audio Handler 是免费的吗？

是的，Audio Handler 完全免费（开源免费），可自由下载、安装和使用。

Audio Handler 支持哪些平台？

Audio Handler 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Audio Handler？

由 Neckr0ik（@neckr0ik）开发并维护，当前版本 v1.0.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论