Du hast einen ComfyUI-Workflow? Erstelle direkt im Browser eine verständliche Workflow-Dokumentation.Workflow verständlich machen.Jetzt ausprobieren ↗
ComfyUI-SparkTTS is a custom ComfyUI node implementation of SparkTTS, an advanced text-to-speech system that harnesses the power of large language models (LLMs) to generate highly accurate and natural-sounding speech.
Paketprofil
README
ComfyUI_SparkTTS is a custom ComfyUI node implementation of SparkTTS, an advanced text-to-speech system that harnesses the power of large language models (LLMs) to generate highly accurate and natural-sounding speech.
SparkTTS_Nodes
Quellen
3 QuellenVerifiziert 10. Sept.
Quellenauszüge
1 AuszugSource context: Repo 1038lab/ComfyUI-SparkTTS
2025/03/21: Update ComfyUI-SparkTTS to v1.1.0 ( update.md )
ComfyUI-SparkTTS provides the following main functionalities:
kokoroTTS_menu
Comfyui-SparkTTS and installinstall requirment.txt in the ComfyUI-SparkTTS folder
./ComfyUI/python_embeded/python -m pip install -r requirements.txt
cd ComfyUI/custom_nodes
git clone https://github.com/1038lab/ComfyUI-SparkTTS
install requirment.txt in the ComfyUI-SparkTTS folder
./ComfyUI/python_embeded/python -m pip install -r requirements.txt
Ensure pip install comfy-cli is installed.
Installing ComfyUI comfy install (if you don't have ComfyUI Installed)
install the ComfyUI-SparkTTS, use the following command:
comfy node registry-install Comfyui-Spark-TTS
install requirment.txt in the ComfyUI-SparkTTS folder
./ComfyUI/python_embeded/python -m pip install -r requirements.txt
ComfyUI/models/TTS/SparkTTS/ when first time using the custom node.ComfyUI/models/TTS/SparkTTS/ folder.This node allows you to create a customized voice by adjusting parameters.
Inputs:
text: Text to synthesize.gender: Gender of the voice (female or male).pitch: Pitch level of the voice (very_low, low, moderate, high, very_high).speed: Speed level of the voice (very_low, low, moderate, high, very_high).batch_texts (optional): Additional texts for better control over pacing and intonation.Outputs:
audio: Generated audio with the customized voice.This node allows you to clone a voice from a reference audio sample.
Inputs:
text: Text to synthesize with the cloned voice.reference_audio: The audio sample to clone the voice from.reference_text: Transcript of the reference audio to improve cloning quality.max_tokens: Controls the maximum length of generated speech.batch_texts (optional): Additional texts for better control over pacing and intonation.Outputs:
audio: Generated audio with the cloned voice.This node allows you to clone a voice from a reference audio with control over pitch and speed.
Inputs:
text: Text to synthesize with the cloned voice.reference_audio: The audio sampleKnoten in diesem Paket
4 Knoten (Plural)Verifiziert 10. Sept.