Convert Text to Speech with Local Kokoro TTS

Convert text to speech—locally, freely, and offline with KOKORO TTS.

This automation connects n8n with KOKORO TTS, a lightweight, high-performing text-to-speech engine that runs entirely on your local machine—no GPU or internet connection required. It’s perfect for creators, developers, and DIY enthusiasts who want to generate natural-sounding voiceovers without relying on paid APIs.

What it does:

🖥️ Runs KOKORO TTS locally via a Python script
🧾 Converts any input text into lifelike speech
🔊 Outputs an MP3 audio file to your defined path
🚫 Works fully offline—no external API needed

✅ Setup guide & importable automation included

Prerequisites:

Python installed

KOKORO TTS (download from GitHub)

Custom voicegen.py script to process input text

n8n installed (self-hosted or desktop)

Defined file output path (e.g., D:\output.mp3)

Customize it your way:

🗂️ Use different voice models available in KOKORO
🛠️ Modify file paths for any OS or directory
🔁 Combine with Telegram or form triggers for on-demand speech generation
🎛️ Add conditional logic to adjust pitch, speed, or voice presets

Need help getting it running? We offer full setup and testing for a one-time fee.