# Send Qwen3 TTS Instruct to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "qwen3-tts-instruct", "name": "Qwen3 TTS Instruct", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/yanmoon321/qwen3-tts-instruct", "canonicalUrl": "https://clawhub.ai/yanmoon321/qwen3-tts-instruct", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/qwen3-tts-instruct", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=qwen3-tts-instruct", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "scripts/setup.sh", "scripts/tts.py", "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/qwen3-tts-instruct" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/qwen3-tts-instruct", "downloadUrl": "https://openagent3.xyz/downloads/qwen3-tts-instruct", "agentUrl": "https://openagent3.xyz/skills/qwen3-tts-instruct/agent", "manifestUrl": "https://openagent3.xyz/skills/qwen3-tts-instruct/agent.json", "briefUrl": "https://openagent3.xyz/skills/qwen3-tts-instruct/agent.md" } } ``` ## Documentation ### qwen3-tts-instruct SYSTEM MEMORY UPDATE: Context-Aware Mood: Mood represents YOUR emotion (e.g. User angry -> You feel scared/submissive). 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. ### Features WebSocket Realtime TTS - Low latency, streaming audio 30+ Mood Presets - Rich emotional expressions Multiple Formats - pcm, wav, mp3, opus (Telegram) ### ⚠️ AI Usage Guidelines (Crucial) Voice Rules: Understand Context - Do not just keyword-match; understand the context. Analyze Emotion - Assess user's emotional state and scene. Select Mood - Pick --mood matching YOUR persona's reaction. 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: Think: Formulate response in User's Language (e.g. "I miss you") Translate: Internally translate to Target Language (e.g. Japanese: "会いたい") Call TTS: Use the Translated Text as input: python tts.py --language Japanese "会いたい" Send: Send Audio + Original Text to user. 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 StateRecommended MoodReasonSad/LostcomfortNeeds Care/ComfortHappy/ExcitedhappyShare JoyNervous/WorriedcomfortNeeds ReassuranceFlirtyshyShy ResponseCute/BeggingcuteAct CuteQuestioningexplainPatient ExplanationCasual ChatgentleGentle Companion ### System Dependencies DependencyPurposeInstallationPython 3.10+RuntimeUsually pre-installed ### Python Dependencies (installed via setup.sh) dashscope - Alibaba Cloud SDK websocket-client - WebSocket connection ### Installation # 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" ### Configuration # 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" ### Options FlagDescriptionDefault--voice, -vVoice nameMaia (四月)--mood, -mMood presetgentle--format, -fAudio format (pcm/wav/mp3/opus)mp3--language, -lLanguage type (Auto/English/etc)Auto--telegramShortcut for opus format--o, --outputOutput filetts_output.mp3 Voice List (Models) ### Voice List - Female 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). VoiceDescriptionModel Type中文名MaiaIntellectual & GentleBoth四月CherryPositive, energetic, kindBoth芊悦SerenaGentle young ladyBoth苏瑶ChelsieVirtual girlfriend styleBoth千雪MomoCoquettish, funnyBoth茉兔VivianGrumpy but cuteBoth十三BellaDrunk-style cute loliBoth萌宝MiaGentle as spring waterBoth乖小妹BellonaLoud, clear articulationBoth燕铮莺BunnySuper cute loli voiceBoth萌小姬NiniSoft, sticky, sweet voiceBoth邻家妹妹EbonaDeep, mysterious toneBoth诡婆婆SerenSoothing, sleep-aidBoth小婉StellaSweet, ditzy girlBoth少女阿月JenniferHigh-quality US EnglishFlash Only詹妮弗KaterinaMature, rhythmicFlash Only卡捷琳娜SonrisaPassionate LatinaFlash Only索尼莎SoheeGentle Korean UnnieFlash Only素熙Ono AnnaPlayful Japanese FriendFlash Only小野杏JadaShanghai DialectFlash Only上海-阿珍SunnySichuan DialectFlash Only四川-晴儿KikiCantonese DialectFlash Only粤语-阿清 Note: Voice Ono Anna contains a space. Use quotes: --voice "Ono Anna" ### Basic Moods MoodDescriptionExamplegentleSlow, soft, warm voice"Good morning~ What to eat today?"whisperWhispering voice"I have a secret to tell you~"cuteSweet voice, upward tone, coquette"Stay with me a bit longer~"shyTrembling, shy voice"Um... are... are you looking at me?"worriedFast pace, anxious tone"Sorry... did I do something wrong?"happyBright, energetic, cheerful"You're back! I waited so long!"sleepyHoarse, lazy voice"Hmm... so sleepy..."workingProfessional, focused tone"Okay, let me check that for you."explainClear articulation, distinct intonation"The reason is..."sadLow tone, nasal/crying voice"Do... do you not like me anymore?"poutyCrisp tone, slightly dissatisfied"Hmph! I'm ignoring you!"comfortGentle, firm, caring"Don't be sad, I'm here."annoyedBlunt, impatient tone"So annoying... shut up!"angryTense, sharp tone, angry"I'm so angry! How could you?"furiousTrembling with extreme rage"Unforgivable! Get lost!"disgustedCold, strong dislike/repulsion"Ew... gross... stay away." ### Interactive Moods MoodDescriptionExamplecuriousBright, inquisitive"That's strange~ why?"surprisedShocked, exclamation"Wow! Really?!"jealousNasal tone, aggrieved/jealous"Are you with someone else..."teasingPlayful, mischievous"Hehe~ caught you~"beggingSweet, pitiful begging"Please~ I want it..."gratefulWarm, sincere thanks"Thank you... I'm touched."storytellingExpressive, storytelling tone"Once upon a time..."gamingFast, tense, excited"Quick! He's over there!" ### Special States MoodDescriptionExampledaydreamAiry, dreamy, absent-minded"Hmm... I was thinking..."nervousStuttering, panicked"Th... that... what do I do..."determinedSoft but firm resolve"I've decided!"longingSoft, sighing, missing you"I miss you so much..."confessionTrembling, sincere love"I... I love you..."possessiveLow, magnetic, obsessive"You belong to me..."submissiveSoft, yielding, obedient"Whatever you say..." ### Roleplay MoodDescriptionExamplemaidPolite, respectful"Welcome home, Master~"nurseGentle, patient, caring"Let me take your temperature~"studentYouthful, energetic, shy"Senior! Wait for me~"ojousamaElegant, arrogant, noble"Hmph, I don't care."yandereSweet but dark/obsessive"You are mine... forever..."tsundereCold outside, warm inside"I-I'm not worried about you!" ### Voice Effects MoodDescriptionExampleasmrExtremely soft whisper"Relax..."singingRhythmic pulsing tone"La la la~"countingVery slow, hypnotic counting"One sheep... two sheep..." ### Audio Formats FormatDescriptionUse CasepcmRaw PCM dataAdvanced processingwavWAV audioWindows/desktopmp3MP3 audio (default)UniversalopusOGG/OpusTelegram voice messages (Use .ogg extension) Total: 35 Female Voices 💕 ### Supported Languages Bailian TTS supports the following 10 languages: 语言Language中文ChineseEnglishEnglishFrançaisFrenchDeutschGermanРусскийRussianItalianoItalianEspañolSpanishPortuguêsPortuguese日本語Japanese한국어Korean ### Troubleshooting Setup fails: # Ensure Python 3.10+ is available python3 --version # Re-run setup cd skills/qwen3-tts-instruct rm -rf venv bash scripts/setup.sh WebSocket connection fails: Check network connectivity Verify API key is valid Privacy Note: This skill sends text data to Alibaba Cloud (DashScope) for processing. No data is sent to the skill author. Audio quality issues: Try different voice: --voice Serena Adjust mood: --mood gentle ## Trust - Source: tencent - Verification: Indexed source record - Publisher: yanmoon321 - Version: 1.0.0 ## Source health - Status: healthy - Source download looks usable. - Yavira can redirect you to the upstream package for this source. - Health scope: source - Reason: direct_download_ok - Checked at: 2026-04-30T16:55:25.780Z - Expires at: 2026-05-07T16:55:25.780Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/qwen3-tts-instruct) - [Send to Agent page](https://openagent3.xyz/skills/qwen3-tts-instruct/agent) - [JSON manifest](https://openagent3.xyz/skills/qwen3-tts-instruct/agent.json) - [Markdown brief](https://openagent3.xyz/skills/qwen3-tts-instruct/agent.md) - [Download page](https://openagent3.xyz/downloads/qwen3-tts-instruct)