ComfyUI Node: StepAudioEditX - Edit ✏️
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
audio/step_audio
Inputs
audio_text STRING
model_path
- (No models found - download Step-Audio-EditX)
device
- cuda
- cpu
torch_dtype
- bfloat16
- float16
- float32
- auto
quantization
- none
- int4
- int8
- int4_awq
attention_mechanism
- sdpa
- eager
- flash_attn
- sage_attn
edit_type
- emotion
- style
- speed
- paralinguistic
- denoising
emotion
- none
- happy
- angry
- sad
- humour
- confusion
- disgusted
- empathy
- embarrass
- fear
- surprised
- excited
- depressed
- coldness
- admiration
- remove
style
- none
- serious
- arrogant
- child
- older
- girl
- pure
- sister
- sweet
- ethereal
- whisper
- gentle
- recite
- generous
- act_coy
- warm
- shy
- comfort
- authority
- chat
- radio
- soulful
- story
- vivid
- program
- news
- advertising
- roar
- murmur
- shout
- deeply
- loudly
- remove
- exaggerated
speed
- none
- faster
- slower
- more faster
- more slower
paralinguistic
- none
- [Breathing]
- [Laughter]
- [Surprise-oh]
- [Confirmation-en]
- [Uhm]
- [Surprise-ah]
- [Surprise-wa]
- [Sigh]
- [Question-ei]
- [Dissatisfaction-hnn]
denoising
- none
- denoise
- vad
paralinguistic_text STRING
n_edit_iterations INT
temperature FLOAT
do_sample BOOLEAN
max_new_tokens INT
seed INT
keep_model_in_vram BOOLEAN
input_audio AUDIO
Outputs
AUDIO
Extension: Step Audio EditX TTS
Professional voice cloning and audio editing node for ComfyUI using Step Audio EditX
Authored by Saganaki22
Looking for a different node?
More nodes in Step Audio EditX TTS
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.