Audio, voice and music skills
Audio skills are SKILL.md folders Claude Code or Codex follow to voice text, generate music and sound effects, transcribe audio to text and set up sound in Unity and Godot games. These are the top 30 by installs. They go in .claude/skills for Claude Code and .agents/skills for Codex.
Ordered by install count from the source, then by repository stars on GitHub. A language model writes each description from the source file; only descriptions that passed the automatic check are listed.
-
1
1,500,000installs
media-use
media-use is a Claude Code skill that finds and generates media for HyperFrames projects, saving files to assets. It handles HeyGen search, voice generation, background audio, and video grading.
skill · heygen-com · Apache-2.0
-
2
387,700installs
elevenlabs-music-generation
elevenlabs-music-generation — a skill for Claude Code, Codex, Cursor, GitHub Copilot and Gemini CLI that calls ElevenLabs Music via the runcomfy CLI and delivers 44.1 kHz stereo audio.
skill · prime-skills · MIT
-
3
379,800installs
ai-music
ai-music — a skill for Claude Code, Codex, Cursor and other agents that generates music through the runcomfy CLI. Routes between ElevenLabs Music ($0.0083/s) and ACE Step ($0.0002–0.0003/s) based on what you actually need.
skill · prime-skills · MIT
-
4
16,900installs
sound-effects · elevenlabs
Creates sound effects from text descriptions with ElevenLabs. Triggers when generating game ambiences, UI chimes, or background audio textures.
skill · elevenlabs · MIT
-
5
16,500installs
ffmpeg
Production-ready FFmpeg recipes for video resizing, compression, audio extraction, and asset preparation for Remotion.
skill · digitalsamba · MIT
-
6
16,200installs
speech-to-text
speech-to-text — a Claude Code skill that transcribes audio and video to text using ElevenLabs Scribe v3. Runs when converting media, generating subtitles, or transcribing meetings.
skill · elevenlabs · MIT
-
7
14,200installs
audio-design
The audio-design skill for Claude Code manages game audio buses, decibel sliders, ducking, and adaptive music. It assists with mixing in Godot, Unity, FMOD, and Wwise.
skill · gamedev-skills · Apache-2.0
-
8
12,200installs
godot-audio
The godot-audio skill runs on Claude Code, Codex, Cursor and other platforms for managing audio APIs in Godot 4.7. It handles player routing, bus layouts, polyphony and headless checks.
skill · gamedev-skills · Apache-2.0
-
9
11,300installs
gemini-live-api-dev official
gemini-live-api-dev guides AI coding assistants in building real-time audio and video apps with Gemini Live API over WebSockets. Handles bidirectional streaming, VAD, and Gemini 3.8 migrations.
skill · google-gemini · Apache-2.0
-
10
9,000installs
edge-tts
Generates MP3 audio from text using Microsoft Edge neural voices through uvx edge-tts. Useful when listening is more convenient than reading while cooking or driving.
skill · aahl · MIT
-
11
8,700installs
transloadit-media-processing official
transloadit-media-processing is a GitHub Copilot skill for processing video, audio, images and documents through Transloadit, including encoding, thumbnails and text extraction.
skill · github · MIT
-
12
7,400installs
openai-whisper
The openai-whisper skill lets your agent call the Whisper CLI to transcribe audio on your own machine. No API key needed.
skill · openclaw · MIT
-
13
7,100installs
optimize-audio
The optimize-audio skill inspects Unity audio settings and helps trace memory use, mixer CPU load, and 3D playback issues.
skill · Unity-Technologies
-
14
6,200installs
qianwen-audio-tts
qianwen-audio-tts is a Claude Code skill that turns text into speech with Qwen TTS models. It handles voiceovers, spoken narration, and text-based audio output.
skill · QianWen-AI · Apache-2.0
-
15
5,500installs
openai-whisper-api
openai-whisper-api — a skill for Claude Code, Codex, Cursor, and other platforms that sends an audio file to OpenAI /v1/audio/transcriptions over curl and writes back the transcript.
skill · openclaw · MIT
-
16
5,100installs
Transcription Automation
Transcription Automation — a skill for automatic audio and video transcription: meeting notes, subtitles, podcast show notes. Runs through the media-mcp server.
skill · Claude Office Skills · MIT
-
17
4,900installs
audio-setup-mixers
audio-setup-mixers sorts Audio Sources into the Audio Mixer groups a Unity project already has. It reads what each source plays, proposes a routing plan, then assigns it.
skill · Unity-Technologies
-
18
4,900installs
layer-audio
layer-audio configures agent prompts for generating sound effects, music, and spoken voice-overs with Layer. Keeps assets dry, sized, and fit for game engines.
skill · layerai · MIT
-
19
4,800installs
Podcast Automation
Podcast Automation runs a podcast episode from raw audio to release: sound processing, show notes, RSS and platform distribution.
skill · Claude Office Skills · MIT
-
20
4,600installs
tesseract-video
tesseract-video is a Claude Code skill that edits existing footage in Tesseract. It shapes the cuts, audio, and graphics around the requested video.
skill · mirage-hq
-
21
4,200installs
fish-audio
Turns text into speech through the AceDataCloud Fish Audio API. It also finds saved voices, builds a permanent public voice model, or makes a one-shot clone from an HTTPS audio link plus exact transcript.
skill · acedatacloud · Apache-2.0
-
22
4,100installs
sound-effects · Barty-Bart
sound-effects — a skill for Claude Code and other agent environments that adds a sound pass to motion graphics: timed effects, music, LUFS mixing. It runs on a finished video and returns a file with frame-level checks.
skill · Barty-Bart · MIT
-
23
4,000installs
videoagent-audio-studio
videoagent-audio-studio routes text-to-speech, music creation, sound effects, and voice cloning to ElevenLabs and fal.ai. Returns ready audio URLs straight inside your coding agent.
skill · wells · MIT
-
24
3,900installs
speech official
speech generates voiceovers, narration, and IVR audio clips via OpenAI Audio API. Useful when your project needs spoken audio files from plain text.
skill · openai · Apache-2.0
-
25
3,800installs
threejs-audio-generator
threejs-audio-generator — a skill that turns ElevenLabs into game audio for Three.js: effects, loops, music and voice lines, written straight into the project.
skill · majidmanzarpour · MIT
-
26
3,500installs
roblox-audio
A skill for Roblox audio work: playback, 3D sound, music, effects and mixing through SoundGroups.
skill · TabooHarmony · MIT
-
27
3,300installs
audioaccessorykit
Guides automatic audio switching setup for third-party Bluetooth headphones with AudioAccessoryKit on iOS 26.4+. Useful when companion apps and extensions handle accessory state.
skill · dpearson2699
-
28
3,100installs
claude-brainrot
The claude-brainrot skill for Claude Code automatically picks and plays memes — image-and-sound combos and standalone sounds — on every response. The UserPromptSubmit hook runs without manual invocation.
skill · marks97
-
29
2,900installs
ai-music-album
Manages end-to-end AI music album production, from concept and lyrics to track sequencing and export. Built for indie projects and brand soundtracks.
skill · nexu-io · Apache-2.0
-
30
2,900installs
zai-tts
zai-tts — a skill that turns text into audio through the GLM-TTS service. Useful when you would rather listen to an agent's answer than read it.
skill · aahl · MIT
How to choose an audio skill
The catalog has 263 audio skills. Most are wrappers around an outside service: ElevenLabs, the OpenAI Audio API, Qwen TTS. Such a skill asks for a key, and speech, music and effects are billed at that service rates. The openai-whisper skill works differently: it runs Whisper transcription on your machine and needs no API key.
Not every service has voices for your language; its documentation says so, not SKILL.md. Nearby: video skills, HyperFrames, games and 3D.
FAQ
Which skill voices text in Claude Code or Codex?
A text-to-speech skill: the list has options on ElevenLabs, the OpenAI Audio API, Qwen TTS and edge-tts with Microsoft Edge voices. By installs, the list is led by media-use, elevenlabs-music-generation and ai-music.
Can I transcribe audio or video to text?
Yes. The openai-whisper skill runs Whisper on your machine with no API key; others send the file to ElevenLabs or the OpenAI API.
Are music and voice skills paid?
The skill itself is free. Generation can cost money: music, effects and speech go through outside services on your key and at their rates.
Other collections
- Best Claude Code skills
- Best Claude Code plugins
- Best Claude Code subagents
- Best Codex skills
- Best Cursor rules
- Best MCP servers
- MCP servers for Cursor
- Frontend skills
- Testing skills
- Security skills and rules
- SEO and marketing skills
- Design skills
- DevOps skills
- MCP servers for databases
- Browser and scraping MCP servers
- Code review and refactoring skills
- Skills and MCP for game development and 3D
- Video generation and editing skills
- Mobile development skills
- Backend and API skills
- Marketing skills and agents
- Scientific skills for AI agents
- UI/UX design skills
- Writing skills
- Claude Code hooks examples
- Claude Code slash commands
- Best Codex plugins
- GitHub Copilot agent skills
- Gemini CLI extensions and skills
- GitHub Copilot instructions
- MCP servers for Claude Code
- MCP servers for Codex
- MCP servers for VS Code
- Remote MCP servers
- Security MCP servers
- Office skills: slides, PDF, Word, Excel
- Data analysis skills
- Research skills
- Telegram AI agent tools
- 1C AI agent tools
- Codex subagents
- Cursor skills
- OpenCode skills
- Animation skills
- Presentation skills
- PDF skills
- Software architecture skills
- Planning and spec skills
- Debugging skills
- Branding and logo skills
- Humanizer and AI-text detector skills
- Game design skills
- Product management skills
- SwiftUI and iOS design skills
- HyperFrames skills
- Figma skills
- Blender skills
- Unity skills
- Godot skills