68 lines
3.3 KiB
Python
68 lines
3.3 KiB
Python
|
"""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")
|