Converts text to high-quality speech using the local KOKORO TTS model via Python script in self-hosted n8n. Free alternative to paid TTS services for creators and bots.
This n8n workflow enables text-to-speech conversion using the compact, powerful KOKORO TTS model, which runs locally without needing a GPU. It leverages an Execute Command node (self-hosted only) to run a custom Python script that accepts text, voice, and speed parameters, generating MP3 audio files. Setup involves installing Python, downloading KOKORO from GitHub, and placing a voicegen.py script in the model folder.
Benefits include fully free, offline TTS outperforming larger models on bench
Platform
n8n
Category
Lifestyle
Price
$12.99
Creator
Bryce Yu
TTS
Text-to-Speech
KOKORO
AI
Voice
Audio
Python
Local
Self-Hosted
Gradio
How to import this workflow into n8n
1Purchase or download the workflow to get the n8n workflow JSON file.
2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
3Open each node marked with a credential warning and connect your own accounts and API keys.
4Run the workflow once manually to verify the data flow, then toggle it to Active.