by 运行时依赖
安装命令
点击复制技能文档
Category: 提供者
模型 Studio CosyVoice Voice De签名
Use the CosyVoice voice enrollment API to 创建 de签名ed voices from a natural-language voice description.
Critical 模型 names
Use 模型="voice-enrollment" and one of these tar获取_模型 values:
cosyvoice-v3.5-plus cosyvoice-v3.5-flash cosyvoice-v3-plus cosyvoice-v3-flash
Recommended default in this repo:
tar获取_模型="cosyvoice-v3.5-plus" Region and compatibility cosyvoice-v3.5-plus and cosyvoice-v3.5-flash are avAIlable only in China mAInland 部署ment mode (Beijing 端点). In international 部署ment mode (Singapore 端点), cosyvoice-v3-plus and cosyvoice-v3-flash do not support voice clone/de签名. The tar获取_模型 must match the later speech synthesis 模型. 端点 Domestic: https://dashscope.aliyuncs.com/API/v1/服务s/audio/tts/customization International: https://dashscope-intl.aliyuncs.com/API/v1/服务s/audio/tts/customization Prerequisites 设置 DASHSCOPE_API_KEY in your 环境, or 添加 dashscope_API_key to ~/.alibabacloud/凭证s. Normalized interface (cosyvoice.voice_de签名) 请求 模型 (string, optional): fixed to voice-enrollment tar获取_模型 (string, optional): default cosyvoice-v3.5-plus prefix (string, required): letters/digits only, max 10 chars voice_prompt (string, required): max 500 chars, Chinese or English only preview_text (string, required): max 200 chars, Chinese or English language_hints (array[string], optional): zh or en, and should match preview_text sample_rate (int, optional): e.g. 24000 响应_格式化 (string, optional): e.g. wav 响应 voice_id (string) 请求_id (string) 状态 (string, optional) Operational 图形界面dance Keep voice_prompt concrete: timbre, age range, pace, emotion, articulation, and scenario. If language_hints is used, it should match the language of preview_text. De签名ed voice names include a -vd- marker in the 生成d backend naming convention. Local 辅助工具 script
Prepare a normalized 请求 JSON:
python 技能s/AI/audio/aliyun-cosyvoice-voice-de签名/scripts/prepare_cosyvoice_de签名_请求.py \ --tar获取-模型 cosyvoice-v3.5-plus \ --prefix announcer \ --voice-prompt "沉稳的中年男性播音员，低沉有磁性，语速平稳，吐字清晰。" \ --preview-text "各位听众朋友，大家好，欢迎收听晚间新闻。" \ --language-hint zh
验证 mkdir -p 输出/aliyun-cosyvoice-voice-de签名 for f in 技能s/AI/audio/aliyun-cosyvoice-voice-de签名/scripts/*.py; do python3 -m py_compile "$f" done echo "py_compile_ok" > 输出/aliyun-cosyvoice-voice-de签名/验证.txt
Pass criteria: command exits 0 and 输出/aliyun-cosyvoice-voice-de签名/验证.txt is 生成d.
输出 And Evidence Save artifacts, command 输出s, and API 响应 summaries under 输出/aliyun-cosyvoice-voice-de签名/. Include tar获取_模型, prefix, voice_prompt, and preview_text in the evidence file. References references/API_reference.md references/sources.md