ComfyUI Node
StepAudioEditX - Edit ✏️
A ComfyUI node in audio/step_audio with 20 inputs and 1 output.
StepAudioEditX - Edit ✏️
- input_audio
- audio
◄audio_text►
◄model_path(No models found - download Step-Audio-EditX)►
◄devicecuda►
◄torch_dtypebfloat16►
◄quantizationnone►
◄attention_mechanismsdpa►
◄edit_typeemotion►
◄emotionnone►
◄stylenone►
◄speednone►
◄paralinguisticnone►
◄denoisingnone►
◄paralinguistic_text►
◄n_edit_iterations1►
◄temperature0.7►
◄do_sampletrue►
◄max_new_tokens8192►
◄seed0►
◄keep_model_in_vramtrue►
Categoryaudio/step_audio
Inputs (20)
| Name | Type | Default | Description |
|---|---|---|---|
| audio_text | STRING | Exact transcript of what the input audio says. The model needs this to understand the content before editing the audio characteristics (emotion, style, speed, etc). | |
| model_path | COMBO | (No models found - download Step-Audio-EditX) | Step-Audio-EditX model location. Place models in ComfyUI/models/step_audio/ or select from discovered models. |
| device | COMBO | cuda | Hardware device: 'cuda' for GPU (10-100x faster, ~8GB VRAM) or 'cpu' (very slow, no VRAM needed). Always use CUDA if available. |
| torch_dtype | COMBO | bfloat16 | Model precision: bfloat16 (best quality, stable, 8GB VRAM), float16 (good quality, 6GB VRAM), float32 (max quality, 16GB VRAM), auto (selects best for your GPU). |
| quantization | COMBO | none | VRAM reduction: 'none' (best quality, 8GB VRAM), int8 (good quality, 4GB VRAM), int4 (acceptable quality, 3GB VRAM), int4_awq (optimized int4, requires pre-quantized model). Use if low on VRAM. |
| attention_mechanism | COMBO | sdpa | Attention layer: sdpa (fastest, good VRAM, default), eager (slowest, most stable), flash_attn (fastest, needs RTX 30xx+), sage_attn (best VRAM efficiency). |
| edit_type | COMBO | emotion | Edit category: emotion (happy, sad, angry), style (whisper, formal), speed (faster/slower), paralinguistic (laughter, breathing), denoising (clean audio). Only one type per edit. |
| emotion | COMBO | none | Target emotion (only if edit_type=emotion): happy, sad, angry, excited, calm, fearful, surprised, disgusted. Changes the emotional tone while keeping voice identity. |
| style | COMBO | none | Speaking style (only if edit_type=style): whisper, gentle, serious, casual, formal, friendly. Changes delivery style while keeping voice and emotion. |
| speed | COMBO | none | Speed adjustment (only if edit_type=speed): faster (1.2x), slower (0.8x), more faster (1.5x), more slower (0.6x). Changes tempo without pitch shift. |
| paralinguistic | COMBO | none | Sound effect (only if edit_type=paralinguistic): [Laughter], [Breathing], [Sigh], [Gasp], [Cough]. Inserts natural non-speech sounds. If paralinguistic_text is empty, auto-appends effect to end of audio. |
| denoising | COMBO | none | Noise removal (only if edit_type=denoising): 'denoise' (remove background noise), 'vad' (voice activity detection, remove silence). Cleans up audio quality. |
| paralinguistic_text | STRING | Text location for effect insertion (only if edit_type=paralinguistic). Example: 'I love this' - effect inserts before/after this phrase. Leave empty to auto-append effect to end of audio_text. | |
| n_edit_iterations | INT | 11–5 | Edit strength through iteration: 1 (subtle change), 2-3 (moderate, recommended), 4-5 (strong, may degrade quality). Each iteration re-applies the edit to amplify the effect. |
| temperature | FLOAT | 0.70.1–2 | Voice variation: 0.1-0.5 (consistent), 0.6-0.8 (natural, recommended), 0.9-1.5 (expressive), 1.6-2.0 (creative). Note: Edit mode hardcoded to 0.7, this parameter has no effect. |
| do_sample | BOOLEAN | true | Sampling mode: True (natural speech) or False (deterministic, greedy decoding). Keep True. Note: Edit mode hardcoded to True, this parameter has no effect. |
| max_new_tokens | INT | 8192256–16384 | Maximum audio tokens to generate: 2048 (~10s), 4096 (~20s), 8192 (~40s). Higher = more VRAM + time. Note: Edit mode hardcoded to 8192, this parameter has no effect. |
| seed | INT | 00–18446744073709550000 | Reproducibility seed: 0 (random output each time) or any number (same input = same output). Use fixed seed to reproduce exact voice outputs. |
| keep_model_in_vram | BOOLEAN | true | Model caching: True (keep loaded, fast repeated use) or False (unload after use, frees ~8GB VRAM). Disable if switching between multiple models frequently. |
| input_audioopt | AUDIO | Source audio to modify (0.5-30 seconds). The AI will apply the selected edit (emotion/style/speed/etc) while preserving voice identity and content. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |