elevenlabs
AI-powered audio generation using ElevenLabs API - text-to-speech with lifelike voices, sound effects generation, and music creation from text descriptions. Generate natural-sounding speech in 32 languages, create custom sound effects for games and videos, and compose royalty-free music tracks. Use this skill when the user requests: - Voice generation or text-to-speech conversion - Audio narration for content (videos, audiobooks, podcasts) - Sound effects for games, videos, or applications - Music generation from text descriptions - Multi-speaker dialogue or conversation audio - Voice cloning
npx skills add majiayu000/claude-skill-registry --skill elevenlabs --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
This skill enables AI-powered audio generation through the ElevenLabs API, offering text-to-speech in 32 languages with 100+ voices, custom voice cloning, real-time streaming, sound effects from text descriptions, and music composition from prompts.
How it works
The skill enumerates three core capabilities:
- Text-to-Speech: supports multiple models (eleven_multilingual_v2, eleven_flash_v2_5, eleven_turbo_v2_5) with features like 100+ voices, multi-speaker dialogue, streaming, and various output formats. It provides examples for basic generation, streaming, and combining multiple voices, and for listing available voices.
- Sound Effects Generation: uses a model eleven_text_to_sound_v2 to produce audio from text prompts, with controls for duration and looping, plus examples for game, UI, and nature sounds; also shows generating multiple effects.
- Music Generation: can compose royalty-free music from prompts, with options for composition plans and genre/style prompts; notes that paid accounts are required for music API. It includes sample code for basic music generation and handling composition plans.
When to use it
Invoke when the user requests voice generation or TTS, audio narration, sound effects, music from text, multi-speaker dialogue, voice cloning, or real-time audio streaming.
What it can touch
The skill references the ElevenLabs API via a Python client (ElevenLabs). It lists sample API usage code including text_to_speech.convert, text_to_sound_effects.convert, text_to_speech.convert_as_stream, voices.get_all, music_generation.compose, and composition_plan.create. It also shows environment variable usage for ELEVENLABS_API_KEY and provides shell commands to set it. It mentions dependency packages: elevenlabs, pydub, python-dotenv.
Caveats
Mentions account requirements: free tier covers TTS and sound effects; music generation requires paid account. Indicates possible errors related to API key, quota, and paid subscription in error handling. Also notes that music generation requires a paid ElevenLabs account and that the API key must be configured as an environment variable; includes guidance on handling restricted prompts.
# ElevenLabs Audio Generation ## Purpose This skill enables AI-powered audio generation through ElevenLabs API. Create lifelike text-to-speech in 32 languages, generate custom sound effects for games and videos, and compose royalty-free music from text descriptions. Support for 100+ professional voices, custom voice cloning, real-time streaming, and multi-speaker dialogue. ## When to Use This skill should be invoked when the user asks to: - Generate speech from text ("convert this to speech", "create audio narration...") - Create voiceovers for videos, presentations, or content - Generate audio in specific voices or languages - Create sound effects ("generate footstep sounds", "create explosion audio...") - Compose music from descriptions ("generate upbeat background music...") - Build multi-speaker dialogue or conversations - Clone voices from audio samples - Stream audio in real-time applications - Create audiobooks, podcasts, or audio content ## Available Capabilities ### 1. Text-to-Speech (Voice Generation) **Models:** - **Eleven Multilingual v2** (`eleven_multilingual_v2`) - Highest quality, 29 languages - **Eleven Flash v2.5** (`eleven_flash_v2_5`) - Ultra-low 75ms latency, 3
- Purpose
- When to Use
- Available Capabilities
- 1. Text-to-Speech (Voice Generation)
- 2. Sound Effects Generation
- 3. Music Generation
- Instructions
- Step 1: Understand the Request
- Step 2: Select Appropriate Model/Capability
- Step 3: Set Up API Authentication
- Step 4: Implement Based on Task Type
- Step 5: Handle Output and Errors
- Step 6: Provide Output to User
- Requirements
export ELEVENLABS_API_KEY="your-api-key-here" pip install elevenlabs pydub python-dotenv
What does the elevenlabs skill do?
AI-powered audio generation using ElevenLabs API - text-to-speech with lifelike voices, sound effects generation, and music creation from text descriptions. Generate natural-sounding speech in 32 languages, create custom sound effects for games and videos, and compose royalty-free music tracks. Use this skill when the user requests: - Voice generation or text-to-speech conversion - Audio narration for content (videos, audiobooks, podcasts) - Sound effects for games, videos, or applications - Music generation from text descriptions - Multi-speaker dialogue or conversation audio - Voice cloning
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill elevenlabs --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.