Extensions/ComfyUI ElevenLabs API integration
ComfyUI Extension

ComfyUI ElevenLabs API integration

This project integrates the ElevenLabs Text-to-Speech API as a custom node for ComfyUI. It enables seamless text-to-speech conversion directly within ComfyUI, providing…

By sysL-padawan·Created about a year ago·Updated 12 months ago· 3
sysL-padawan/comfyui-elevenlabs-integration
Nodes2
On cloudLocal install
CategoryElevenlabs API integration by 奥利奥
Stars3
Updated12 months ago

Nodes (2)

ElevenlabsTextToEffect
Elevenlabs API integration by 奥利奥
ElevenlabsTextToSpeech
Elevenlabs API integration by 奥利奥
Readme

ComfyUI ElevenLabs API integration

This ComfyUI node adds text-to-speech capabilities using the ElevenLabs API. If you enjoy using it and want to support my work, feel free to buy me a coffee — it’s much appreciated!

<a href="https://buymeacoffee.com/aoliao" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/default-orange.png" alt="Buy Me A Coffee" height="40" width="174"></a>

text-to-voice text-to-effect

Installation

Install via the ComfyUI Manager or clone the repo into your custom_nodes folder:

git clone https://github.com/sysL-padawan/comfyui-elevenlabs-integration.git

Then change into the directory and install the dependencies:

pip install -r requirements.txt

Finally, restart ComfyUI.

Nodes

Currently, there is one node for text-to-speech with ElevenLabs.

ElevenlabsTextToSpeech

  • api_key: Your ElevenLabs API key
  • voice_id: The voice ID from ElevenLabs
  • model_id: The desired model (e.g. eleven_multilingual_v2)
  • text: The text to be spoken
  • output_format: Optional, e.g. mp3_44100_128 (default)
  • seed: Optional, for reproducible results
  • apply_text_normalization: Optional, choose between auto, on, or off
  • voice_settings_stability: Optional, float (0.0–1.0), controls emotional range
  • voice_settings_use_speaker_boost: Optional, boolean, boosts similarity to original speaker
  • voice_settings_similarity_boost: Optional, float (0.0–1.0), how closely to match the original voice
  • voice_settings_style: Optional, float (0.0–1.0), amplifies speaker style
  • voice_settings_speed: Optional, float (0.5–2.0), adjusts speech speed

The node returns an audio tensor and the sample rate, which can be used directly for e.g. LipSync.

Example Workflow

  1. Generate text-to-speech with ElevenLabs.
  2. Use the audio output for LipSync or other audio applications.

ElevenlabsTextToEffect

  • api_key: Your ElevenLabs API key
  • text: The text to be converted into a sound effect
  • duration: (Optional) Length of the effect in seconds (default: 3, range: 1–22)
  • prompt_influence: (Optional) Influence of the text prompt on the generated effect (default: 0.3, range: 0–1)
  • output_format: (Optional) e.g. mp3_44100_128 (default)

The node returns an audio tensor and the sample rate, which can be used directly for further audio applications.

Example Workflow

  1. Generate a sound effect from text with ElevenLabs.
  2. Use the audio output for sound design, effects, or other audio applications.

License

Credits