ComfyUI Node: CSM Text-to-Speech with Context

Authored by thezveroboy

Created

Updated

34 stars

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

zveroboy/CSM

Inputs

text STRING
model_path STRING
tokenizer_path STRING
sample_rate INT
audio_context AUDIO
context_transcription STRING
context_speaker INT
speaker INT
max_audio_length_ms FLOAT
temperature FLOAT
topk INT

Outputs

AUDIO

Extension: ComfyUI-CSM-Nodes

Custom nodes for ComfyUI implementing the csm model for text-to-speech generation.

Authored by thezveroboy

Looking for a different node?

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.

Learn more