feat: add DashScope custom voice enrollment flow

backend/routes/model_registry.py

@@ -20,6 +20,7 @@ from schemas import (
     ModelResourceUpsert,
 )
 from services.auth import require_admin
+from services.dashscope_voice import VoiceRequest, manage_voice
 from services.interface_catalog import validate_fields
 from services.masking import mask_secrets, merge_secrets
 from services.model_resource_tester import test_model_resource
@@ -377,3 +378,16 @@ async def delete_model_resource(
     await session.delete(row)
     await session.commit()
     return {"ok": True}
+
+
+@router.post("/model-resources/dashscope/voice")
+async def manage_dashscope_voice(request: VoiceRequest, session: AsyncSession = Depends(get_session)):
+    """Create/query a voice using draft settings and server-held credentials."""
+    stored = {}
+    if request.resource_id:
+        row = await session.get(ModelResource, request.resource_id)
+        if not row or row.interface_type != "dashscope-tts":
+            raise HTTPException(404, "百炼 TTS 模型资源不存在")
+        stored = row.secrets or {}
+    key = merge_secrets({"apiKey": request.api_key}, stored).get("apiKey", "")
+    return await manage_voice(request, key)

backend/services/dashscope_voice.py

@@ -0,0 +1,67 @@
+"""DashScope voice enrollment, separate from the real-time synthesis path."""
+import base64
+import re
+from typing import Literal
+from urllib.parse import urlsplit
+
+import httpx
+from fastapi import HTTPException
+from pydantic import BaseModel, Field
+from services.pipecat.dashscope_tts import SUPPORTED_MODELS
+
+
+class VoiceRequest(BaseModel):
+    resource_id: str | None = Field(default=None, alias="resourceId")
+    api_key: str = Field(default="", alias="apiKey", max_length=4096)
+    api_url: str = Field(alias="apiUrl", max_length=2048)
+    model: str
+    action: Literal["create_voice", "query_voice"]
+    prefix: str = Field(default="assistant", pattern=r"^[A-Za-z0-9]{1,10}$")
+    audio: str = Field(default="", max_length=14_000_000)
+    voice_id: str = Field(default="", alias="voiceId", max_length=512)
+
+
+def enrollment_payload(request: VoiceRequest):
+    host = urlsplit(request.api_url).hostname or ""
+    allowed = host in {"dashscope.aliyuncs.com", "dashscope-intl.aliyuncs.com"} or re.fullmatch(
+        r"[a-zA-Z0-9-]+\.(cn-beijing|ap-southeast-1)\.maas\.aliyuncs\.com", host)
+    if not allowed:
+        raise HTTPException(400, "音色复刻仅支持百炼北京或新加坡官方域名")
+    if request.model not in SUPPORTED_MODELS or request.model == "cosyvoice-v1":
+        raise HTTPException(400, "当前模型不支持此声音复刻流程")
+    data = {"action": request.action}
+    if request.action == "create_voice":
+        match = re.fullmatch(r"data:audio/(wav|x-wav|mpeg|mp3|mp4|m4a|x-m4a);base64,(.+)", request.audio)
+        if not match:
+            raise HTTPException(400, "请上传 WAV、MP3 或 M4A 音频")
+        try:
+            raw = base64.b64decode(match[2], validate=True)
+        except ValueError:
+            raise HTTPException(400, "音频编码不合法")
+        if not raw or len(raw) > 10 * 1024 * 1024:
+            raise HTTPException(400, "音频必须非空且不超过 10 MB")
+        data.update(target_model=request.model, prefix=request.prefix, audio=request.audio)
+    else:
+        if not request.voice_id:
+            raise HTTPException(400, "缺少音色 ID")
+        data["voice_id"] = request.voice_id
+    return f"https://{host}/api/v1/services/audio/tts/customization", {"model": "voice-enrollment", "input": data}
+
+
+async def manage_voice(request: VoiceRequest, api_key: str):
+    if not api_key:
+        raise HTTPException(400, "请先填写 API Key")
+    url, payload = enrollment_payload(request)
+    try:
+        async with httpx.AsyncClient(timeout=60) as client:
+            response = await client.post(url, json=payload, headers={"Authorization": f"Bearer {api_key}"})
+        if response.is_error:
+            raise HTTPException(502, f"百炼音色服务请求失败（HTTP {response.status_code}），请检查凭据、模型和录音要求")
+        output = response.json()["output"]
+        if request.action == "create_voice":
+            return {"voiceId": output["voice_id"], "status": "DEPLOYING"}
+        if output.get("target_model") != request.model:
+            raise HTTPException(400, "此音色绑定的模型与当前选择不一致")
+        return {"voiceId": request.voice_id, "status": output["status"]}
+    except (httpx.HTTPError, ValueError, KeyError, TypeError):
+        raise HTTPException(502, "音色服务连接异常或返回无效，请稍后查询；创建结果不确定时不要重复创建")

backend/tests/test_dashscope_voice.py

@@ -0,0 +1,25 @@
+import unittest
+from fastapi import HTTPException
+from services.dashscope_voice import VoiceRequest, enrollment_payload
+
+
+class VoiceEnrollmentTests(unittest.TestCase):
+    def request(self, **changes):
+        return VoiceRequest.model_validate({"apiUrl": "wss://dashscope.aliyuncs.com/api-ws/v1/inference", "model": "cosyvoice-v3-plus", "action": "create_voice", "audio": "data:audio/wav;base64,UklGRg==", **changes})
+
+    def test_creation_and_region(self):
+        url, payload = enrollment_payload(self.request())
+        self.assertEqual(url, "https://dashscope.aliyuncs.com/api/v1/services/audio/tts/customization")
+        self.assertEqual(payload["input"]["target_model"], "cosyvoice-v3-plus")
+
+    def test_no_credentials_to_arbitrary_host(self):
+        with self.assertRaises(HTTPException):
+            enrollment_payload(self.request(apiUrl="https://evil.example"))
+
+    def test_query_needs_id(self):
+        with self.assertRaises(HTTPException):
+            enrollment_payload(self.request(action="query_voice"))
+
+    def test_invalid_audio(self):
+        with self.assertRaises(HTTPException):
+            enrollment_payload(self.request(audio="data:audio/wav;base64,???"))

frontend/src/components/models/DashscopeVoice.tsx

@@ -0,0 +1,61 @@
+"use client";
+
+import { useState } from "react";
+import { modelResourcesApi } from "@/lib/api";
+import { Button } from "@/components/ui/button";
+import { Input } from "@/components/ui/input";
+
+export function DashscopeVoice({ resourceId, apiKey, apiUrl, model, onApply }: {
+  resourceId?: string; apiKey: string; apiUrl: string; model: string; onApply: (voice: string) => void;
+}) {
+  const [audio, setAudio] = useState("");
+  const [voiceId, setVoiceId] = useState("");
+  const [status, setStatus] = useState("");
+  const [busy, setBusy] = useState(false);
+  const [message, setMessage] = useState("");
+
+  async function upload(file?: File) {
+    setAudio("");
+    setMessage("");
+    if (!file) return;
+    const extension = file.name.split(".").pop()?.toLowerCase();
+    if (!extension || !["wav", "mp3", "m4a"].includes(extension) || !file.size || file.size > 10 * 1024 * 1024) {
+      setMessage("请选择不超过 10 MB 的 WAV、MP3 或 M4A 文件"); return;
+    }
+    setBusy(true);
+    try {
+      const encoded = await new Promise<string>((resolve, reject) => {
+        const reader = new FileReader();
+        reader.onload = () => resolve(String(reader.result).split(",")[1]);
+        reader.onerror = () => reject(new Error("读取录音失败"));
+        reader.readAsDataURL(file);
+      });
+      setAudio(`data:audio/${extension === "mp3" ? "mpeg" : extension};base64,${encoded}`);
+    } catch { setMessage("读取录音失败"); }
+    finally { setBusy(false); }
+  }
+
+  async function run(action: "create_voice" | "query_voice") {
+    setBusy(true); setMessage("");
+    try {
+      const result = await modelResourcesApi.voice({ resourceId, apiKey, apiUrl, model, action, audio: action === "create_voice" ? audio : undefined, voiceId });
+      setVoiceId(result.voiceId); setStatus(result.status);
+      setMessage(result.status === "OK" ? "音色已就绪，可以应用到当前配置" : result.status === "DEPLOYING" ? "音色处理中，请稍后查询状态" : "音色不可用，请检查录音要求");
+    } catch (error) { setMessage(error instanceof Error ? error.message : "音色请求失败"); }
+    finally { setBusy(false); }
+  }
+
+  return <div className="space-y-3 rounded-xl border border-border p-4">
+    <div className="text-sm font-medium">自定义音色 · 声音复刻</div>
+    <p className="text-xs text-muted-foreground">上传本人或已获授权的清晰录音，推荐 10–20 秒，最长 60 秒，采样率至少 16 kHz。音色仅用于当前模型；切换模型需重新创建。</p>
+    <Input type="file" accept=".wav,.mp3,.m4a" disabled={busy} aria-label="参考录音" onChange={event => void upload(event.target.files?.[0])} />
+    <Button type="button" variant="outline" disabled={busy || !audio || Boolean(voiceId)} onClick={() => void run("create_voice")}>创建音色</Button>
+    <p className="text-xs text-muted-foreground">也可以粘贴已有音色 ID，查询就绪后应用。</p>
+    <Input value={voiceId} disabled={busy} aria-label="自定义音色 ID" placeholder="音色 ID" onChange={event => { setVoiceId(event.target.value); setStatus(""); setMessage(""); }} />
+    <div className="flex flex-wrap gap-2">
+      <Button type="button" variant="outline" disabled={busy || !voiceId} onClick={() => void run("query_voice")}>查询状态</Button>
+      <Button type="button" disabled={busy || status !== "OK"} onClick={() => { onApply(voiceId); setMessage("已填入音色字段，请测试连接并保存模型资源"); }}>使用此音色</Button>
+    </div>
+    {message && <p role="status" className="text-xs text-muted-foreground">{message}</p>}
+  </div>;
+}

frontend/src/components/pages/ComponentsModelsPage.tsx

@@ -16,6 +16,7 @@ import {
 } from "lucide-react";
 import { useCallback, useEffect, useMemo, useState } from "react";
 
+import { DashscopeVoice } from "@/components/models/DashscopeVoice";
 import { Badge } from "@/components/ui/badge";
 import { Button } from "@/components/ui/button";
 import {
@@ -807,6 +808,19 @@ export function ComponentsModelsPage() {
               </FieldSection>
 
               <FieldSection title="连接与鉴权信息" scrollable fill>
+                {draft.interfaceType.startsWith("dashscope-") && (
+                  <a href="https://help.aliyun.com/zh/model-studio/get-api-key" target="_blank" rel="noopener noreferrer" className="text-xs text-primary underline underline-offset-4">获取百炼 API Key 与鉴权说明 ↗</a>
+                )}
+                {draft.interfaceType === "dashscope-tts" && (
+                  <DashscopeVoice
+                    key={`${editingId ?? "new"}:${draft.values.model}:${draft.values.apiUrl}`}
+                    resourceId={editingId ?? undefined}
+                    apiKey={String(draft.secrets.apiKey || storedSecretMasks.apiKey || "")}
+                    apiUrl={String(draft.values.apiUrl || "")}
+                    model={String(draft.values.model || "")}
+                    onApply={voice => { setDraft(previous => ({ ...previous, values: { ...previous.values, voice } })); setTestResult(null); }}
+                  />
+                )}
                 {connectionFields.map((field) => (
                   <DynamicField
                     key={`${field.group}-${field.key}`}

frontend/src/lib/api.ts

@@ -229,6 +229,8 @@ export const interfaceDefinitionsApi = {
 };
 
 export const modelResourcesApi = {
+  voice: (body: { resourceId?: string; apiKey: string; apiUrl: string; model: string; action: "create_voice" | "query_voice"; audio?: string; voiceId?: string }) =>
+    request<{ voiceId: string; status: string }>("/api/model-resources/dashscope/voice", { method: "POST", body: JSON.stringify(body) }),
   list: () => request<ModelResource[]>("/api/model-resources"),
   create: (body: ModelResourceUpsert) =>
     request<ModelResource>("/api/model-resources", {