xiaoxia/xiaoxia-saas
1
0
Fork 0
Code Issues 24 Pull Requests 5 Actions 1 Packages Projects Releases 7 Wiki Activity

fix: CosyVoice默认模型改为v3-flash+音色名加_v3后缀，修复418错误
CI/CD Pipeline / Validate Code Quality And Tests (pull_request) Failing after 8s
Details
CI/CD Pipeline / Frontend Lint (pull_request) Successful in 50s
Details
CI/CD Pipeline / Build & Push Staging (Watchtower auto-deploy) (pull_request) Has been skipped
Details
CI/CD Pipeline / Build Production Runtime Images (pull_request) Has been skipped
Details
CI/CD Pipeline / Staging E2E Tests (pull_request) Has been skipped
Details
CI/CD Pipeline / Staging API Integration Tests (pull_request) Has been skipped
Details
CI/CD Pipeline / Deploy Production (pull_request) Has been skipped
Details
CI/CD Pipeline / Production Browser E2E (pull_request) Has been skipped
Details

Browse Source 
根因：cosyvoice-v3.5-plus 无系统音色，使用系统音色必然返回418。

修复：
1. 默认合成模型从 cosyvoice-v3.5-plus 改为 cosyvoice-v3-flash
   - v3-flash 支持31个系统音色，速度更快，成本更低
   - v3.5-plus 仅支持克隆/设计音色，不适合作为默认模型
2. 8个预置音色全部加上 _v3 后缀（适配v3系列命名规范）
3. 默认音色从 longxiaochun 改为 longxiaochun_v3
4. 更新所有相关测试用例
This commit is contained in:
用户CI Test
2026-07-11 01:46:06 +08:00
parent a25e0b6220
commit c51dc17618
3 changed files with 13 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/shared/config.py
+2 -2
View File
@@ -32,8 +32,8 @@ class SharedSettings(BaseSettings):
# CosyVoice (阿里云百炼语音合成)
cosyvoice_api_key: str = ""
cosyvoice_base_url: str = "https://dashscope.aliyuncs.com/api/v1"
cosyvoice_model: str = "cosyvoice-v3.5-plus"
cosyvoice_voice: str = "longxiaochun_v3" # 默认音色
cosyvoice_model: str = "cosyvoice-v3-flash"
cosyvoice_voice: str = "longxiaochun_v3" # 默认音色（v3 系列系统音色带 _v3 后缀）
cosyvoice_sample_rate: int = 22050
cosyvoice_format: str = "mp3" # 输出格式：mp3/wav/pcm
# 音色克隆模型名（固定为 voice-enrollment）