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 or custom voice creation - Audio streaming for real-time applications Capabilities: Text-to-speech (32 languages, 100+ voices), sound effects generation, music composition, voice cloning, real-time audio streaming Python SDK: elevenlabs (pip install elevenlabs)
AI-powered audio generation using ElevenLabs API - text-to-speech, sound effects, and music creation.
This skill enables Claude Code to generate professional-quality audio using ElevenLabs API. Create lifelike text-to-speech in 32 languages with 100+ voices, generate custom sound effects for games and videos, and compose royalty-free music from text descriptions. Perfect for content creation, game development, e-learning, podcasts, and multimedia production.
# Install the skill
skillz install elevenlabs
# Or copy to your project
cp -r skills/creative/elevenlabs .claude/skills/
API Key:
# Get API key from https://elevenlabs.io/app/settings/api-keys
export ELEVENLABS_API_KEY="your-api-key-here"
Python Dependencies:
pip install elevenlabs pydub python-dotenv
System:
Once installed, simply ask Claude to generate audio:
"Convert this text to speech using a professional voice"
"Generate footstep sound effects for my game"
"Create upbeat background music for my video"
"Make an audiobook narration of this chapter"
Claude will automatically:
Features:
Models:
Use Cases:
Features:
Use Cases:
Features:
Requirements:
Use Cases:
references/text-to-speech.md - Complete TTS documentation
references/sound-effects.md - Sound effects generation guide
references/music-generation.md - Music creation documentation
from elevenlabs.client import ElevenLabs
client = ElevenLabs(api_key="your-key")
audio = client.text_to_speech.convert(
text="Chapter text here...",
voice_id="JBFqnCBsd6RMkjVDRZzb", # George - narrative voice
model_id="eleven_multilingual_v2"
)
# Save to file
with open("chapter.mp3", "wb") as f:
for chunk in audio:
f.write(chunk)
audio = client.text_to_sound_effects.convert(
text="sword whooshing through air, fast combat swing",
duration_seconds=1.5
)
with open("sword_swing.mp3", "wb") as f:
for chunk in audio:
f.write(chunk)
audio = client.music_generation.compose(
prompt="""Upbeat corporate background music with piano and strings,
professional and inspiring""",
music_length_ms=60000 # 60 seconds
)
with open("background.mp3", "wb") as f:
for chunk in audio:
f.write(chunk)
Popular Voices:
JBFqnCBsd6RMkjVDRZzb) - Male, narrative21m00Tcm4TlvDq8ikWAM) - Female, calmTxGEqnHWrfWFTfGW9XjX) - Male, energeticEXAVITQu4vr4xnSDxMaL) - Female, expressiveList all voices:
voices = client.voices.get_all()
for voice in voices.voices:
print(f"{voice.name}: {voice.voice_id}")
from elevenlabs import stream
audio_stream = client.text_to_speech.convert_as_stream(
text="This is streamed in real-time",
voice_id="JBFqnCBsd6RMkjVDRZzb",
model_id="eleven_flash_v2_5" # Low latency
)
stream(audio_stream) # Play immediately
speakers = [
("JBFqnCBsd6RMkjVDRZzb", "Hello, how are you?"),
("21m00Tcm4TlvDq8ikWAM", "I'm doing great, thanks!"),
]
# Generate and combine (see examples for full implementation)
Check current pricing: https://elevenlabs.io/pricing
Choose Right Model:
Select Appropriate Voice:
Optimize for Use Case:
Be Descriptive:
Set Appropriate Duration:
Adjust Prompt Influence:
Detailed Prompts:
Avoid Copyrighted Material:
Plan Duration:
# Verify API key is set
echo $ELEVENLABS_API_KEY
# Set if missing
export ELEVENLABS_API_KEY="your-key-here"
Text-to-Speech:
Need highest quality? → eleven_multilingual_v2
Need low latency? → eleven_flash_v2_5
General use? → eleven_turbo_v2_5
Cost-conscious? → eleven_flash_v2_5
Sound Effects:
eleven_text_to_sound_v2Music:
#!/usr/bin/env python3
import os
from elevenlabs.client import ElevenLabs
client = ElevenLabs(api_key=os.environ["ELEVENLABS_API_KEY"])
# Your audio generation code
# Flask example
from flask import Flask, send_file
from elevenlabs.client import ElevenLabs
app = Flask(__name__)
client = ElevenLabs()
@app.route("/generate/<text>")
def generate(text):
audio = client.text_to_speech.convert(text=text, ...)
return send_file(audio, mimetype="audio/mpeg")
texts = ["Text 1", "Text 2", "Text 3"]
for i, text in enumerate(texts):
audio = client.text_to_speech.convert(text=text, ...)
with open(f"output_{i}.mp3", "wb") as f:
for chunk in audio:
f.write(chunk)
image-generation - AI image creation (Gemini, DALL-E)python-plotting - Audio visualizationscientific-writing - Generate narration textpython-best-practices - Clean audio processing codeImprovements welcome:
For issues or questions:
Ready to create amazing audio! 🎵🎙️🔊
Using ElevenLabs API for professional audio generation
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.
Extract frames or short clips from videos using ffmpeg.
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.
Category:media-generate