Loading...
Loading...
Complete ElevenLabs AI audio platform: text-to-speech (TTS), speech-to-text (STT/Scribe), voice cloning, voice design, sound effects, music generation, dubbing, voice changer, voice isolator, and conversational voice agents. Use when working with audio generation, voice synthesis, transcription, audio processing, or building voice-enabled applications. Triggers: generate speech, clone voice, transcribe audio, create sound effects, compose music, dub video, change voice, isolate vocals, build voice agent, ElevenLabs API/SDK/CLI/MCP.
npx skill4agent add jakerains/agentskills elevenlabs| Capability | API/Tool | Use Case |
|---|---|---|
| Text-to-Speech | | Generate lifelike speech from text |
| Speech-to-Text | | Transcribe audio with Scribe v2 |
| Voice Cloning | | Clone voices from audio samples |
| Voice Design | | Create voices from text descriptions |
| Sound Effects | | Generate SFX from prompts |
| Music | | Generate studio-grade music |
| Dubbing | Dubbing API | Translate video/audio (32 languages) |
| Voice Changer | | Transform voice while preserving emotion |
| Voice Isolator | | Remove background noise |
| Voice Agents | Agents CLI/API | Build conversational AI agents |
# Environment variable
export ELEVENLABS_API_KEY="your-api-key"
# Or in .env file
ELEVENLABS_API_KEY=your-api-key# Python
pip install elevenlabs
# TypeScript/Node
npm install elevenlabs{
"mcpServers": {
"ElevenLabs": {
"command": "uvx",
"args": ["elevenlabs-mcp"],
"env": {
"ELEVENLABS_API_KEY": "your-api-key"
}
}
}
}from elevenlabs.client import ElevenLabs
from elevenlabs import play
client = ElevenLabs(api_key="your-api-key")
audio = client.text_to_speech.convert(
text="Hello world!",
voice_id="JBFqnCBsd6RMkjVDRZzb", # George
model_id="eleven_multilingual_v2",
output_format="mp3_44100_128"
)
play(audio)mcp__ElevenLabs__text_to_speech
- text: "Your text here"
- voice_name: "Rachel" (or voice_id)
- model_id: "eleven_multilingual_v2"
- stability: 0.5, similarity_boost: 0.75
- speed: 1.0 (range: 0.7-1.2)| Model | Latency | Languages | Best For |
|---|---|---|---|
| ~500ms | 29 | High quality, long-form |
| ~75ms | 32 | Real-time, agents |
| ~250ms | 32 | Balanced quality/speed |
| Higher | 70+ | Emotional, dramatic |
result = client.speech_to_text.convert(
file=open("audio.mp3", "rb"),
model_id="scribe_v2",
diarize=True # Speaker detection
)
print(result.text)mcp__ElevenLabs__speech_to_text
- input_file_path: "/path/to/audio.mp3"
- diarize: true (speaker detection)
- language_code: "eng" (or auto-detect)mcp__ElevenLabs__voice_clone
- name: "My Voice"
- files: ["/path/to/sample1.mp3", "/path/to/sample2.mp3"]
- description: "Professional male voice"mcp__ElevenLabs__text_to_voice
- voice_description: "A warm, friendly male voice with a slight British accent,
perfect for audiobook narration"create_voice_from_previewmcp__ElevenLabs__text_to_sound_effects
- text: "Heavy wooden door creaking open slowly"
- duration_seconds: 3.0 (0.5-30 seconds)
- loop: falsemcp__ElevenLabs__compose_music
- prompt: "Upbeat electronic track with driving synths, 120 BPM"
- music_length_ms: 60000 (10s-5min)mcp__ElevenLabs__speech_to_speech
- input_file_path: "/path/to/recording.mp3"
- voice_id: "target_voice_id"mcp__ElevenLabs__isolate_audio
- input_file_path: "/path/to/noisy_audio.mp3"# Install
npm install -g @elevenlabs/cli
# Initialize and authenticate
elevenlabs agents init
elevenlabs auth login
# Create agent
elevenlabs agents add "Support Bot" --template customer-service
# Deploy
elevenlabs agents push| Template | Use Case |
|---|---|
| Professional support, low temp |
| General purpose, balanced |
| Voice interactions only |
| Text conversations only |
| Quick prototyping |
mcp__ElevenLabs__search_voices
- search: "professional narrator"
- sort: "name" | "created_at_unix"mcp__ElevenLabs__search_voice_library
- search: "deep male"
- page_size: 10| Voice | ID | Style |
|---|---|---|
| Rachel | 21m00Tcm4TlvDq8ikWAM | Neutral, professional |
| Adam | pNInz6obpgDQGcFmaJgB | Deep, warm |
| Bella | EXAVITQu4vr4xnSDxMaL | Soft, gentle |
mcp__ElevenLabs__check_subscriptionmcp__ElevenLabs__list_models| Topic | File |
|---|---|
| TTS Models & Parameters | references/tts-models.md |
| Speech-to-Text (Scribe) | references/stt-scribe.md |
| Sound Effects Prompting | references/sound-effects.md |
| Music Generation | references/music-generation.md |
| Voice Agents (CLI/API) | references/voice-agents.md |
| Agent Prompting Guide | references/agent-prompting.md |
| Dubbing Guide | references/dubbing.md |
| Plan | Multilingual v2 | Flash/Turbo | STT |
|---|---|---|---|
| Free | 2 | 4 | 8 |
| Starter | 3 | 6 | 12 |
| Creator | 5 | 10 | 20 |
| Pro | 10 | 20 | 40 |
| Scale | 15 | 30 | 60 |