aliang-bailian-voice-clone
starsforks
How to install aliang-bailian-voice-clone?
aliang2052/aliang-skills/aliang-bailian-voice-clone
$npx -y skills add aliang2052/aliang-skills --skill aliang-bailian-voice-clone使用百炼已创建的克隆音色（CosyVoice v3.5-flash）通过 bl speech synthesize 合成语音。
SKILL.md
| 1 | # 百炼克隆音色语音合成 Skill |
| 2 | |
| 3 | ## 触发词 |
| 4 | |
| 5 | 当用户说"用阿亮的声音"、"克隆声音"、"声音合成"、"TTS"时使用。 |
| 6 | |
| 7 | ## 重要发现 |
| 8 | |
| 9 | - **DashScope 声音复刻 API 端点**（`/compatible-mode/v1/audio/voices`）**返回 404**，无法通过 curl 或 SDK 直接创建克隆音色。 |
| 10 | - 声音克隆必须在**百炼控制台**（console）中手动创建。 |
| 11 | - 克隆音色创建后，可通过 `bl speech synthesize` 直接使用，传入完整的 voice ID 即可。 |
| 12 | |
| 13 | ## 已有阿亮音色 |
| 14 | |
| 15 | | 场景 | 音色 ID | |
| 16 | |------|---------| |
| 17 | | 日常/温暖 | `cosyvoice-v3.5-flash-YOUR_WARM_VOICE_ID` | |
| 18 | | 科技风 | `cosyvoice-v3.5-flash-YOUR_TECH_VOICE_ID` | |
| 19 | |
| 20 | ## 使用方法 |
| 21 | |
| 22 | ### 基本命令 |
| 23 | |
| 24 | ```bash |
| 25 | bl speech synthesize \ |
| 26 | --text "{要合成的文本}" \ |
| 27 | --model cosyvoice-v3.5-flash \ |
| 28 | --voice {音色ID} \ |
| 29 | --out {输出路径.mp3} \ |
| 30 | --language zh |
| 31 | ``` |
| 32 | |
| 33 | ### 示例：用阿亮科技音色合成新闻 |
| 34 | |
| 35 | ```bash |
| 36 | bl speech synthesize \ |
| 37 | --text "Anthropic 发布新一代旗舰模型 Claude Opus 4.8..." \ |
| 38 | --model cosyvoice-v3.5-flash \ |
| 39 | --voice cosyvoice-v3.5-flash-YOUR_TECH_VOICE_ID \ |
| 40 | --out 输出/阿亮科技新闻.mp3 \ |
| 41 | --language zh |
| 42 | ``` |
| 43 | |
| 44 | ## 参数说明 |
| 45 | |
| 46 | | 参数 | 说明 | |
| 47 | |------|------| |
| 48 | | `--model` | 必须使用 `cosyvoice-v3.5-flash`（克隆音色专用模型） | |
| 49 | | `--voice` | 完整的克隆音色 ID（含前缀 `cosyvoice-v3.5-flash-`） | |
| 50 | | `--language` | `zh`（中文）或 `en`（英文） | |
| 51 | | `--rate` | 语速 0.5-2.0（默认 1.0） | |
| 52 | | `--pitch` | 音调 0.5-2.0（默认 1.0） | |
| 53 | | `--volume` | 音量 0-100（默认 50） | |
| 54 | | `--out` | 输出文件路径（mp3/wav/pcm/opus） | |
| 55 | |
| 56 | ## 注意事项 |
| 57 | |
| 58 | - `cosyvoice-v3-flash`（系统音色）和 `cosyvoice-v3.5-flash`（克隆音色）是**不同模型**，不能混用。 |
| 59 | - 系统音色用 `--model cosyvoice-v3-flash --voice longanyang` 等。 |
| 60 | - 克隆音色用 `--model cosyvoice-v3.5-flash --voice cosyvoice-v3.5-flash-xxx-xxx`。 |
| 61 | - 如果用户需要新增克隆音色，需引导其前往百炼控制台操作，CLI 无法直接创建。 |
People who liked this also viewed
6 picksType
- ai-video-generationinference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agentsSkillsJul 2026
- imagegen-frontend-webElite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing pageSkillsJul 2026
- hyperframes-mediaWrite HTML. Render video. Built for agents.SkillsJul 2026
- media-useAgent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + leSkillsJul 2026
- general-videoAuthor or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, staticSkillsJul 2026
- product-launch-videoTurn a product or marketing URL, pasted script, or brief into a product launch / promo video — SaaS promos, feature reveals, product demos, app and company launches. Use when the user wants to market,SkillsJul 2026
