From fbbed439bd844d58482b183a261e61cbc754695f Mon Sep 17 00:00:00 2001
From: zhixian <zhixian@bunker.local>
Date: Sun, 25 Jan 2026 14:22:05 +0900
Subject: [PATCH] feat(tts): support custom OpenAI-compatible TTS endpoints

Add OPENAI_TTS_BASE_URL environment variable to allow using self-hosted
or third-party OpenAI-compatible TTS services like Kokoro, LocalAI, or
OpenedAI-Speech.

Changes:
- Add OPENAI_TTS_BASE_URL env var (defaults to OpenAI official API)
- Relax model/voice validation when using custom endpoints
- Add tts-1 and tts-1-hd to the model allowlist

This enables users to:
- Use local TTS for privacy and cost savings
- Use models with better non-English language support (Chinese, Japanese)
- Reduce latency with local inference

Example usage:
  OPENAI_TTS_BASE_URL=http://localhost:8880/v1

Tested with Kokoro-FastAPI.
---
 src/tts/tts.ts | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/src/tts/tts.ts b/src/tts/tts.ts
index 5fa06f8d4..41a829433 100644
--- a/src/tts/tts.ts
+++ b/src/tts/tts.ts
@@ -736,7 +736,15 @@ function parseTtsDirectives(
   };
 }
 
-export const OPENAI_TTS_MODELS = ["gpt-4o-mini-tts"] as const;
+export const OPENAI_TTS_MODELS = ["gpt-4o-mini-tts", "tts-1", "tts-1-hd"] as const;
+
+/**
+ * Custom OpenAI-compatible TTS endpoint.
+ * When set, model/voice validation is relaxed to allow non-OpenAI models.
+ * Example: OPENAI_TTS_BASE_URL=http://localhost:8880/v1
+ */
+const OPENAI_TTS_BASE_URL = process.env.OPENAI_TTS_BASE_URL?.trim() || "https://api.openai.com/v1";
+const isCustomOpenAIEndpoint = OPENAI_TTS_BASE_URL !== "https://api.openai.com/v1";
 export const OPENAI_TTS_VOICES = [
   "alloy",
   "ash",
@@ -752,10 +760,14 @@ export const OPENAI_TTS_VOICES = [
 type OpenAiTtsVoice = (typeof OPENAI_TTS_VOICES)[number];
 
 function isValidOpenAIModel(model: string): boolean {
+  // Allow any model when using custom endpoint (e.g., Kokoro, LocalAI)
+  if (isCustomOpenAIEndpoint) return true;
   return OPENAI_TTS_MODELS.includes(model as (typeof OPENAI_TTS_MODELS)[number]);
 }
 
 function isValidOpenAIVoice(voice: string): voice is OpenAiTtsVoice {
+  // Allow any voice when using custom endpoint (e.g., Kokoro Chinese voices)
+  if (isCustomOpenAIEndpoint) return true;
   return OPENAI_TTS_VOICES.includes(voice as OpenAiTtsVoice);
 }
 
@@ -982,7 +994,7 @@ async function openaiTTS(params: {
   const timeout = setTimeout(() => controller.abort(), timeoutMs);
 
   try {
-    const response = await fetch("https://api.openai.com/v1/audio/speech", {
+    const response = await fetch(`${OPENAI_TTS_BASE_URL}/audio/speech`, {
       method: "POST",
       headers: {
         Authorization: `Bearer ${apiKey}`,