From 631279bd3a56261acd571c106638e006ebbf9587 Mon Sep 17 00:00:00 2001
From: prosolis <5590409+prosolis@users.noreply.github.com>
Date: Fri, 26 Jun 2026 15:10:36 -0700
Subject: [PATCH] TTS: auto-detect Chinese vs English so callers can pass the
 selection

speak()'s lang now defaults to detectLang(text) (any Han/kana -> zh-CN,
else en-US) instead of always en-US, so reading a Chinese passage picks the
Piper zh voice rather than spelling out characters with the English voice.
Explicit lang still overrides.

Claude-Session: https://claude.ai/code/session_016Yr6jELuRc7hyzYLccQKZd
---
 web/src/audio/speech.ts | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/web/src/audio/speech.ts b/web/src/audio/speech.ts
index f540e56..3d7cda8 100644
--- a/web/src/audio/speech.ts
+++ b/web/src/audio/speech.ts
@@ -59,12 +59,23 @@ function speakWebSpeech(text: string, lang: string): void {
   synth.speak(utterance)
 }
 
+// detectLang guesses a BCP-47 locale from the text so the right Piper voice is
+// chosen. Any Han/kana character routes to Chinese (zh-CN) — a selection is
+// essentially never mixed at the level that matters, and reading a Chinese
+// passage with the English voice spells each character out ("Chinese letter…").
+// Everything else defaults to US English, the language she's learning.
+const CJK = /[぀-ヿ㐀-䶿一-鿿豈-﫿ｦ-ﾟ]/
+export function detectLang(text: string): string {
+  return CJK.test(text) ? 'zh-CN' : 'en-US'
+}
+
 // speak reads `text` aloud, cancelling anything already in flight so rapid taps
-// don't queue up. `lang` defaults to US English (the language she's learning);
-// pass a zh locale to hear a Chinese passage. It tries the server's neural voice
-// first and silently falls back to the browser voice if that's unavailable (route
-// off, network error, or a 404 for a language with no configured voice).
-export function speak(text: string, lang = 'en-US'): void {
+// don't queue up. `lang` defaults to a guess from the text (Chinese vs English)
+// so callers can just pass the selection; pass an explicit locale to override.
+// It tries the server's neural voice first and silently falls back to the browser
+// voice if that's unavailable (route off, network error, or a 404 for a language
+// with no configured voice).
+export function speak(text: string, lang = detectLang(text)): void {
   if (!text.trim()) return
   stopCurrent()
   const seq = ++requestSeq