From 676a6111fc99680372effe73869436fbda1a5b9c Mon Sep 17 00:00:00 2001
From: Chiranjeet Mishra <chiranjeet@vapi.ai>
Date: Wed, 14 Oct 2026 03:47:24 +0000
Subject: [PATCH] docs: document the MiniMax voice region field

MinimaxVoice.region accepts worldwide (default) or china. worldwide uses
MiniMax's US West endpoint and there is no EU endpoint.
---
 fern/providers/voice/minimax.mdx | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/fern/providers/voice/minimax.mdx b/fern/providers/voice/minimax.mdx
index dd4e21daf..1586c5df6 100644
--- a/fern/providers/voice/minimax.mdx
+++ b/fern/providers/voice/minimax.mdx
@@ -36,6 +36,21 @@ For additional API configuration options, review the [`MinimaxVoice` fields](/ap
 
 MiniMax offers many voices and supports voice cloning, you can browse and copy a voice's ID from the [Voice Library](/providers/voice/overview). The default voice is `socialmedia_female_1_v1`.
 
+### Region (`region`)
+
+`voice.region` selects which MiniMax API endpoint Vapi connects to. It accepts `worldwide` (default) or `china`. `worldwide` uses MiniMax's US West endpoint; `china` uses MiniMax's mainland China endpoint. There is no EU endpoint.
+
+```json
+{
+  "voice": {
+    "provider": "minimax",
+    "model": "speech-02-turbo",
+    "voiceId": "socialmedia_female_1_v1",
+    "region": "china"
+  }
+}
+```
+
 ### Subtitle timing for live captions (`subtitleType`)
 
 MiniMax can return subtitle data alongside synthesized audio, which Vapi forwards through the [`assistant.speechStarted`](/server-url/events#assistant-speech-started) client/server message. This is intended for live caption UIs and karaoke-style word highlighting.