ComfyUI Node: 🔊 Geeky Kokoro Advanced Voice
Category
audio
Inputs
audio AUDIO
effect_blend FLOAT
voice_morph
- None
- Child
- Teen
- Adult
- Elder
- Feminine
- Masculine
- Neutral
- Androgynous
morph_intensity FLOAT
enable_pitch_formant BOOLEAN
pitch_shift FLOAT
formant_shift FLOAT
auto_tune FLOAT
enable_time BOOLEAN
time_stretch FLOAT
vibrato FLOAT
vibrato_speed FLOAT
enable_spatial BOOLEAN
reverb_amount FLOAT
reverb_room_size FLOAT
reverb_damping FLOAT
echo_delay FLOAT
echo_feedback FLOAT
enable_tone BOOLEAN
bass_boost FLOAT
mid_boost FLOAT
treble_boost FLOAT
harmonics FLOAT
enable_effects BOOLEAN
distortion FLOAT
tremolo FLOAT
bitcrush FLOAT
noise_reduction FLOAT
enable_dynamics BOOLEAN
compression FLOAT
limit_ceiling FLOAT
warmth FLOAT
character_effect
- None
- Robot
- Telephone
- Megaphone
- Radio
- Underwater
- Cosmic
- Whisper
- ASMR
- Demon
- Angel
- Alien
- 8-bit Game
- Darth Vader
character_intensity FLOAT
preset
- None
- Chipmunk
- Deep Voice
- Helium
- Phone Call
- Child Voice
- Elder Voice
- Robot Voice
- Ethereal
- Monster
- Ghost
- Fantasy Elf
- Dwarf
- Orc
- Celestial
- Demonic
- Radio Host
- Podcast
- Movie Trailer
- Storyteller
- Singer
- Darth Vader
- Underwater
- TV Announcer
preset_strength FLOAT
Outputs
AUDIO
Extension: ComfyUI-TimestepShiftModel
This is a ComfyUI implementation of the timestep shift technique used in a/NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training. For more details, visit the official a/NitroFusion GitHub repository.
Authored by ChenDarYen
Run ComfyUI workflows in the Cloud!
No downloads or installs are required. Pay only for active GPU usage, not idle time. No complex setups and dependency issues
Learn more