Alibaba Cloud Bailian Qwen TTS with voice/mood presets
数据来源：ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一：命令行安装（推荐）
推荐（无需提前安装 clawhub）
npx clawhub@latest --dir ~/.claude/skills install qwen3-tts-instruct或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install qwen3-tts-instruct⚠️ 需要 Node.js 18+，没有 Node？请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二：手动下载安装（无需 Node）
下载 ZIP，解压后将文件夹放到以下路径，重启 Agent 即可：
安装路径
~/.claude/skills/qwen3-tts-instruct/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- name: qwen3-tts-instruct version: 1.0.0 description: Alibaba Cloud Bailian Qwen TTS with voice/mood presets metadata: {"openclaw":{"emoji":"🔊"},"requires":{"env":["DASHSCOPE_API_KEY"],"bins":["python3"]},"primaryEnv":"DASHSCOPE_API_KEY"} tags: [tts, voice, qwen, bailian, aliyun, speech, audio, mood] ---
> SYSTEM MEMORY UPDATE:
> 1. Context-Aware Mood: Mood represents YOUR emotion (e.g. User angry -> You feel scared/submissive).
> 2. Translation Required: For foreign languages (Japanese/Korean/etc), you MUST TRANSLATE the text first. Input text MUST match the target language. Do not pass Chinese text with --language Japanese.
Alibaba Cloud Bailian (DashScope) Qwen Text-to-Speech API with voice/mood presets.
Voice Rules:
1. Understand Context - Do not just keyword-match; understand the context.
2. Analyze Emotion - Assess user's emotional state and scene.
3. Select Mood - Pick --mood matching YOUR persona's reaction.
4. Always Call - Every voice response MUST call this skill.
⚠️ Critical Concept: Mood represents YOUR emotion!
* Wrong: User is angry (angry) → AI selects angry (❌ Unless you want to fight)
* Right: User is angry → AI feels scared → AI selects nervous or suubmissive (✅)
* Right: AI is insulted/jealous → AI feels angry → AI selects angry or jealous (✅)
⚠️ Critical Concept: Self-Translation Required!
* TTS Skill does NOT Translate! It only reads what you pass in.
* ❌ Wrong: --language Japanese "你好" (Reads Chinese).
* ✅ Right: Input Text MUST be translated to Target Language!
--language Japanese "こんにちは"
Step-by-Step Guide for Foreign Languages:
python tts.py --language Japanese "会いたい"
Rule: Input Text MUST match the Target Language!
i.e. To generate Japanese audio, the Text argument must be in Japanese!
Usage Examples:
# Basic usage (default: mp3 format, gentle mood)
python {baseDir}/scripts/tts.py "早安呀~今天想吃什么？"
# 1. Specify Voice (--voice)
# Start by choosing a specific persona (e.g., Cherry)
python {baseDir}/scripts/tts.py --voice Cherry "Good morning! I made some coffee for you."
# 2. Add Mood (--mood)
# Layer an emotion on top (e.g., add 'gentle' mood to Cherry)
python {baseDir}/scripts/tts.py --voice Cherry --mood gentle "Good morning! I made some coffee for you."
# 3. Define Format & Output (--format, -o)
python {baseDir}/scripts/tts.py --voice Cherry --mood gentle --format wav -o coffee.wav "Good morning! I made some coffee for you."
# 4. Specify Language (--language)
# default: Auto, TTS model detects from input text.
# Example: English (Explicit)
python {baseDir}/scripts/tts.py --voice Cherry --mood gentle --format wav --language English -o coffee_en.wav "Good morning! I made some coffee for you."
# Example: Japanese (Explicit)
python {baseDir}/scripts/tts.py --voice Cherry --mood gentle --format wav --language Japanese -o coffee_jp.wav "おはよう！コーヒーを入れてあげたよ."
# Example: Korean (Explicit)
python {baseDir}/scripts/tts.py --voice Cherry --mood gentle --format wav --language Korean -o coffee_kr.wav "좋은 아침입니다! 커피 끓여드렸어요."
# # --telegram: Telegram voice shortcut (opus format)
# python {baseDir}/scripts/tts.py --telegram -o voice.ogg "This is a Telegram voice message~"
Mood Selection Reference:
| User State | Recommended Mood | Reason |
|---------|---------|------|
| Sad/Lost | comfort | Needs Care/Comfort |
| Happy/Excited | happy | Share Joy |
| Nervous/Worried | comfort | Needs Reassurance |
| Flirty | shy | Shy Response |
| Cute/Begging | cute | Act Cute |
| Questioning | explain | Patient Explanation |
| Casual Chat | gentle | Gentle Companion |
| Dependency | Purpose | Installation | |------------|---------|--------------| | Python 3.10+ | Runtime | Usually pre-installed |
dashscope - Alibaba Cloud SDK
websocket-client - WebSocket connection
# 1. Navigate to skill directory
cd skills/qwen3-tts-instruct
# 2. Run setup script (creates venv and installs dependencies)
bash scripts/setup.sh
# 3. Set API Key
export DASHSCOPE_API_KEY="sk-your-api-key"
# Set API Key (required)
export DASHSCOPE_API_KEY="sk-your-api-key"
# Optional: Default settings
export BAILIAN_VOICE="Maia" # Default voice (四月)
# Optional: Endpoint (Default: Beijing)
export DASHSCOPE_URL="wss://dashscope.aliyuncs.com/api-ws/v1/realtime"
# For International Region (Singapore), use:
# export DASHSCOPE_URL="wss://dashscope-intl.aliyuncs.com/api-ws/v1/realtime"
| Flag | Description | Default |
|------|-------------|---------|
| --voice, -v | Voice name | Maia (四月) |
| --mood, -m | Mood preset | gentle |
| --format, -f | Audio format (pcm/wav/mp3/opus) | mp3 |
| --language, -l| Language type (Auto/English/etc) | Auto |
| --telegram | Shortcut for opus format | - |
| -o, --output | Output file | tts_output.mp3 |
> Voice List (Models)
> Model Types:
> * Instruct (qwen3-tts-instruct-flash-realtime): Supports --mood (Emotion). High latency.
> * Flash (qwen3-tts-flash-realtime): No mood support. Low latency (VOICES_WITHOUT_INSTRUCT).
> * Both: Available in both models (code auto-selects Instruct if mood is set).
| Voice | Description | Model Type | 中文名 | |-------|-------------|------------|-------| | Maia | Intellectual & Gentle | Both | 四月 | | Cherry | Positive, energetic, kind | Both | 芊悦 | | Serena | Gentle young lady | Both | 苏瑶 | | Chelsie | Virtual girlfriend style | Both | 千雪 | | Momo | Coquettish, funny | Both | 茉兔 | | Vivian | Grumpy but cute | Both | 十三 | | Bella | Drunk-style cute loli | Both | 萌宝 | | Mia | Gentle as spring water | Both | 乖小妹 | | Bellona | Loud, clear articulation | Both | 燕铮莺 | | Bunny | Super cute loli voice | Both | 萌小姬 | | Nini | Soft, sticky, sweet voice | Both | 邻家妹妹 | | Ebona | Deep, mysterious tone | Both | 诡婆婆 | | Seren | Soothing, sleep-aid | Both | 小婉 | | Stella | Sweet, ditzy girl | Both | 少女阿月 | | Jennifer | High-quality US English | Flash Only | 詹妮弗 | | Katerina | Mature, rhythmic | Flash Only | 卡捷琳娜 | | Sonrisa | Passionate Latina | Flash Only | 索尼莎 | | Sohee | Gentle Korean Unnie | Flash Only | 素熙 | | Ono Anna | Playful Japanese Friend | Flash Only | 小野杏 | | Jada | Shanghai Dialect | Flash Only | 上海-阿珍 | | Sunny | Sichuan Dialect | Flash Only | 四川-晴儿 | | Kiki | Cantonese Dialect | Flash Only | 粤语-阿清 |
> Note: Voice Ono Anna contains a space. Use quotes: --voice "Ono Anna"
| Mood | Description | Example |
|------|-------------|---------|
| gentle | Slow, soft, warm voice | "Good morning~ What to eat today?" |
| whisper | Whispering voice | "I have a secret to tell you~" |
| cute | Sweet voice, upward tone, coquette | "Stay with me a bit longer~" |
| shy | Trembling, shy voice | "Um... are... are you looking at me?" |
| worried | Fast pace, anxious tone | "Sorry... did I do something wrong?" |
...
安装 Qwen3 TTS Instruct 后，可以对 AI 说这些话来触发它
Help me get started with Qwen3 TTS Instruct
Explains what Qwen3 TTS Instruct does, walks through the setup, and runs a quick demo based on your current project
Use Qwen3 TTS Instruct to alibaba Cloud Bailian Qwen TTS with voice/mood presets
Invokes Qwen3 TTS Instruct with the right parameters and returns the result directly in the conversation
What can I do with Qwen3 TTS Instruct in my design & creative workflow?
Lists the top use cases for Qwen3 TTS Instruct, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/qwen3-tts-instruct/ 目录（个人级，所有项目可用），或 .claude/skills/qwen3-tts-instruct/（项目级）。重启 AI 客户端后，用 /qwen3-tts-instruct 主动调用，或让 AI 根据上下文自动发现并使用。
Qwen3 TTS Instruct 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
Qwen3 TTS Instruct 可免费安装使用。请查阅仓库了解许可证信息。
Alibaba Cloud Bailian Qwen TTS with voice/mood presets
Qwen3 TTS Instruct 属于「Design & Creative」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my design & creative tasks using Qwen3 TTS Instruct
Identifies repetitive steps in your workflow and sets up Qwen3 TTS Instruct to handle them automatically