From eb8a0308a3a7d4019c6f407c8528e8e820b567b5 Mon Sep 17 00:00:00 2001
From: Ayo <ayo@ayco.io>
Date: Fri, 22 May 2026 20:34:50 +0200
Subject: [PATCH] chore: explain that each voice need to be downloaded once
 before using offline

---
 README.md | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/README.md b/README.md
index 770b6a2..ae3fdd0 100644
--- a/README.md
+++ b/README.md
@@ -165,6 +165,10 @@ python tts.py "Hello there! and Hi!" -t "simple-greetings"
 ls ./outputs/simple-greetings
 ```
 
+### Offline Use
+
+Each of the [voices below](#voices) need to be downloaded once the first time they are used, and this needs an online connection. Subsequent runs can be done offline.
+
 ### Voices
 
 You can choose a voice to use with the `--voice` flag. For this, we use [kokoro](https://huggingface.co/hexgrad/Kokoro-82M), which is an Apache-licensed model. See [all available voices](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md).