Elevenlabs-ComfyUI

Elevenlabs-ComfyUI

ElevenLabs API Integration for ComfyUI

Complete suite of 13 nodes providing full access to ElevenLabs AI audio capabilities including text-to-speech, voice cloning, dubbing, sound effects, music generation, and more.

License: MIT Python 3.8+ ComfyUI

---

📋 Table of Contents

• Features
• Installation
• Getting Your API Key
• Available Nodes
• Quick Start
• Troubleshooting
• License

---

✨ Features

• 13 Specialized Nodes covering all ElevenLabs API endpoints
• Auto-Refresh voices when API key changes
• V3 Model Support with emotional expressiveness (70+ languages)
• Voice Cloning from audio samples
• Dubbing for video localization
• Sound Effects generation from text
• Music Generation with AI
• Voice Isolation to remove background noise
• Account Management to check credits and usage
• Comprehensive Error Logging for debugging

---

🚀 Installation

Method 1: ComfyUI Manager (Recommended)

1. Open ComfyUI Manager

2. Search for "Elevenlabs-ComfyUI"

3. Click Install

Method 2: Manual Installation

cd  ComfyUI/custom_nodes/
git  clone  https://github.com/karthikg-09/Elevenlabs-ComfyUI.git
cd  Elevenlabs-ComfyUI
pip  install  -r  requirements.txt

Method 3: Portable/Standalone Installation

cd  ComfyUI_windows_portable/ComfyUI/custom_nodes/
git  clone  https://github.com/karthikg-09/Elevenlabs-ComfyUI.git
cd  Elevenlabs-ComfyUI
../../python_embeded/python.exe  -m  pip  install  -r  requirements.txt

Restart ComfyUI after installation.

---

🔑 Getting Your API Key

1. Visit ElevenLabs
2. Sign up for a free account (or log in)
3. Navigate to your Profile Settings
4. Click "Generate API Key"
5. Copy the API key
6. Paste it into the api_key field in any node

Note: Keep your API key secure and never share it publicly.

---

📦 Available Nodes

All nodes are located in the "ElevenLabs" category in ComfyUI's Add Node menu.

1. ElevenLabs TTS (Text-to-Speech)

Convert text to natural-sounding speech with full control over voice characteristics.

Inputs:

• api_key (STRING) - Your ElevenLabs API key

• text (STRING) - Text to synthesize (3K-40K character limit depending on model)

• voice (DROPDOWN) - Voice selection from your account (auto-populated)

• model (DROPDOWN) - AI model (eleven_v3, eleven_multilingual_v2, eleven_turbo_v2_5, etc.)

• stability (FLOAT 0-1) - Voice consistency - Lower = more expressive, Higher = more stable

• similarity_boost (FLOAT 0-1) - How closely output matches original voice characteristics

• style (FLOAT 0-1) - Emotional expressiveness - Higher = more dramatic (especially for eleven_v3)

• use_speaker_boost (BOOLEAN) - Enhance voice clarity and cloning accuracy (recommended: ON)

• language_code (DROPDOWN) - Target language (or "auto" for automatic detection)

• output_format (DROPDOWN) - Audio format: mp3_44100_128, pcm_16000, pcm_44100, etc.

• seed (INT) - Seed for reproducible generation (-1 for random)

Outputs:

• AUDIO - Generated speech audio (compatible with ComfyUI audio nodes)

Use Cases: Voiceovers, audiobooks, narration, character dialogue, e-learning content

---

2. ElevenLabs Speech-to-Text

Transcribe spoken audio into text with high accuracy (99 languages supported).

Inputs:

• api_key (STRING) - Your ElevenLabs API key

• audio (AUDIO) - Audio input to tr