接入边缘浏览器语音合成并做本地缓存，听书段落可直接朗读。

依赖随锁文件一并落下，避免环境缺包。

Co-authored-by: Cursor <cursoragent@cursor.com>

src/tts/cache.ts

@@ -0,0 +1,42 @@
+import { createHash } from "node:crypto";
+import { existsSync, mkdirSync, readFileSync, writeFileSync } from "node:fs";
+import path from "node:path";
+import { getUserDataDir } from "../config/user-data-dir.js";
+
+function cacheDir(): string {
+  const dir = path.join(getUserDataDir(), "tts-cache");
+  mkdirSync(dir, { recursive: true });
+  return dir;
+}
+
+export function ttsCacheKey(parts: {
+  provider: string;
+  voice: string;
+  text: string;
+  extra?: string;
+}): string {
+  const h = createHash("sha256");
+  h.update(parts.provider);
+  h.update("\0");
+  h.update(parts.voice);
+  h.update("\0");
+  h.update(parts.extra ?? "");
+  h.update("\0");
+  h.update(parts.text);
+  return h.digest("hex").slice(0, 40);
+}
+
+export function readTtsCache(key: string, ext: string): Buffer | null {
+  const file = path.join(cacheDir(), `${key}.${ext}`);
+  if (!existsSync(file)) return null;
+  try {
+    return readFileSync(file);
+  } catch {
+    return null;
+  }
+}
+
+export function writeTtsCache(key: string, ext: string, data: Buffer): void {
+  const file = path.join(cacheDir(), `${key}.${ext}`);
+  writeFileSync(file, data);
+}

src/tts/edge.ts

@@ -0,0 +1,109 @@
+import { MsEdgeTTS, OUTPUT_FORMAT } from "msedge-tts";
+import { readTtsCache, ttsCacheKey, writeTtsCache } from "./cache.js";
+import {
+  DEFAULT_EDGE_VOICE,
+  type TtsSynthesizeParams,
+  type TtsSynthesizeResult,
+} from "./types.js";
+
+/** Edge SSML 单段不宜过长；按句切到约此字数 */
+const CHUNK_TARGET = 1200;
+
+function escapeXml(text: string): string {
+  return text
+    .replace(/&/g, "&")
+    .replace(/</g, "&lt;")
+    .replace(/>/g, "&gt;")
+    .replace(/"/g, "&quot;")
+    .replace(/'/g, "&apos;");
+}
+
+function resolveVoice(explicit?: string): string {
+  const fromEnv = process.env.WRITING_AGENT_TTS_VOICE?.trim();
+  return (explicit?.trim() || fromEnv || DEFAULT_EDGE_VOICE).trim();
+}
+
+function splitChunks(text: string): string[] {
+  const cleaned = text.replace(/\r\n/g, "\n").trim();
+  if (!cleaned) return [];
+  if (cleaned.length <= CHUNK_TARGET) return [cleaned];
+
+  const parts: string[] = [];
+  let buf = "";
+  const pushBuf = () => {
+    const t = buf.trim();
+    if (t) parts.push(t);
+    buf = "";
+  };
+
+  const sentences = cleaned.split(/(?<=[。！？!?；;\n])/u);
+  for (const s of sentences) {
+    if (!s) continue;
+    if (buf.length + s.length > CHUNK_TARGET && buf.length > 0) {
+      pushBuf();
+    }
+    buf += s;
+    if (buf.length >= CHUNK_TARGET) pushBuf();
+  }
+  pushBuf();
+  return parts.length ? parts : [cleaned.slice(0, CHUNK_TARGET)];
+}
+
+async function streamToBuffer(
+  audioStream: NodeJS.ReadableStream,
+): Promise<Buffer> {
+  const chunks: Buffer[] = [];
+  for await (const chunk of audioStream) {
+    chunks.push(Buffer.isBuffer(chunk) ? chunk : Buffer.from(chunk));
+  }
+  return Buffer.concat(chunks);
+}
+
+async function synthesizeChunk(voice: string, text: string): Promise<Buffer> {
+  const tts = new MsEdgeTTS();
+  await tts.setMetadata(voice, OUTPUT_FORMAT.AUDIO_24KHZ_48KBITRATE_MONO_MP3);
+  const { audioStream } = tts.toStream(escapeXml(text));
+  return streamToBuffer(audioStream);
+}
+
+/**
+ * Edge 在线神经 TTS（微软朗读通道）。文本会发往微软服务端。
+ */
+export async function synthesizeWithEdge(
+  params: TtsSynthesizeParams,
+): Promise<TtsSynthesizeResult> {
+  const text = params.text.trim();
+  if (!text) throw new Error("TTS 文本为空");
+  const voice = resolveVoice(params.voice);
+  const key = ttsCacheKey({
+    provider: "edge",
+    voice,
+    text,
+    extra: params.cacheKey,
+  });
+  const hit = readTtsCache(key, "mp3");
+  if (hit) {
+    return {
+      audio: hit,
+      contentType: "audio/mpeg",
+      provider: "edge",
+      voice,
+      cached: true,
+    };
+  }
+
+  const chunks = splitChunks(text);
+  const buffers: Buffer[] = [];
+  for (const chunk of chunks) {
+    buffers.push(await synthesizeChunk(voice, chunk));
+  }
+  const audio = Buffer.concat(buffers);
+  writeTtsCache(key, "mp3", audio);
+  return {
+    audio,
+    contentType: "audio/mpeg",
+    provider: "edge",
+    voice,
+    cached: false,
+  };
+}

src/tts/index.ts

@@ -0,0 +1,42 @@
+import { synthesizeWithEdge } from "./edge.js";
+import {
+  DEFAULT_TTS_PROVIDER,
+  type TtsProviderId,
+  type TtsSynthesizeParams,
+  type TtsSynthesizeResult,
+} from "./types.js";
+
+export {
+  DEFAULT_EDGE_VOICE,
+  DEFAULT_TTS_PROVIDER,
+  type TtsProviderId,
+  type TtsSynthesizeParams,
+  type TtsSynthesizeResult,
+} from "./types.js";
+
+export function resolveTtsProvider(): TtsProviderId {
+  const raw = (process.env.WRITING_AGENT_TTS_PROVIDER ?? DEFAULT_TTS_PROVIDER)
+    .trim()
+    .toLowerCase();
+  if (raw === "local" || raw === "tencent" || raw === "edge") return raw;
+  return DEFAULT_TTS_PROVIDER;
+}
+
+/**
+ * 统一合成入口。当前仅实现 edge；local / tencent 占位。
+ */
+export async function synthesizeSpeech(
+  params: TtsSynthesizeParams,
+): Promise<TtsSynthesizeResult> {
+  const provider = resolveTtsProvider();
+  if (provider === "edge") {
+    return synthesizeWithEdge(params);
+  }
+  if (provider === "local") {
+    throw new Error("本地 TTS 尚未接入；请将 WRITING_AGENT_TTS_PROVIDER=edge");
+  }
+  if (provider === "tencent") {
+    throw new Error("腾讯云 TTS 尚未接入；请将 WRITING_AGENT_TTS_PROVIDER=edge");
+  }
+  return synthesizeWithEdge(params);
+}

src/tts/types.ts

@@ -0,0 +1,22 @@
+/** TTS 提供方（默认 edge；本地/腾讯后接） */
+
+export type TtsProviderId = "edge" | "local" | "tencent";
+
+export type TtsSynthesizeParams = {
+  text: string;
+  /** 缓存键额外盐（如 sectionId），便于按节失效 */
+  cacheKey?: string;
+  voice?: string;
+};
+
+export type TtsSynthesizeResult = {
+  audio: Buffer;
+  contentType: string;
+  provider: TtsProviderId;
+  voice: string;
+  cached: boolean;
+};
+
+export const DEFAULT_TTS_PROVIDER: TtsProviderId = "edge";
+/** 听书默认中文声线 */
+export const DEFAULT_EDGE_VOICE = "zh-CN-XiaoxiaoNeural";