diff --git a/backend/routes/model_registry.py b/backend/routes/model_registry.py index 768eb71..3b63787 100644 --- a/backend/routes/model_registry.py +++ b/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) diff --git a/backend/services/dashscope_voice.py b/backend/services/dashscope_voice.py new file mode 100644 index 0000000..81ae9fa --- /dev/null +++ b/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") diff --git a/backend/tests/test_dashscope_voice.py b/backend/tests/test_dashscope_voice.py new file mode 100644 index 0000000..095459d --- /dev/null +++ b/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,???")) diff --git a/frontend/src/components/models/DashscopeVoice.tsx b/frontend/src/components/models/DashscopeVoice.tsx new file mode 100644 index 0000000..f0f76d1 --- /dev/null +++ b/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((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
+
自定义音色 · 声音复刻
+

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。

+ void upload(event.target.files?.[0])} /> + +

也可以粘贴已有音色 ID，查询就绪后应用。

+ { setVoiceId(event.target.value); setStatus(""); setMessage(""); }} /> +
+ + +
+ {message &&

{message}

} +
; +} diff --git a/frontend/src/components/pages/ComponentsModelsPage.tsx b/frontend/src/components/pages/ComponentsModelsPage.tsx index c3933a7..49abc84 100644 --- a/frontend/src/components/pages/ComponentsModelsPage.tsx +++ b/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() { + {draft.interfaceType.startsWith("dashscope-") && ( + 获取百炼 API Key 与鉴权说明 ↗ + )} + {draft.interfaceType === "dashscope-tts" && ( + { setDraft(previous => ({ ...previous, values: { ...previous.values, voice } })); setTestResult(null); }} + /> + )} {connectionFields.map((field) => ( + request<{ voiceId: string; status: string }>("/api/model-resources/dashscope/voice", { method: "POST", body: JSON.stringify(body) }), list: () => request("/api/model-resources"), create: (body: ModelResourceUpsert) => request("/api/model-resources", {