Перейти к содержимому
TakoAPI
Назад к навыкам

qwen3-tts-instruct

от yanmoon321

DevOps & Cloud
815Число загрузок по данным clawskills.sh
1Звёзды
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

Alibaba Cloud Bailian Qwen TTS with voice/mood presets.

Описание

Что делает этот навык

Generates text-to-speech audio using Alibaba Cloud's DashScope (Bailian) Qwen TTS API via WebSocket streaming. Supports over 30 mood presets, 35 female voices, and 10 languages including Japanese and Korean. The agent picks moods based on its own emotional reaction to the conversation, not the user's state.

The 30+ named mood presets (nervous, jealous, yandere, asmr, etc.) produce emotionally nuanced speech that generic TTS APIs can't replicate without custom prosody tuning.

Когда его использовать

  • Voicing AI companion replies with contextually matched emotions
  • Sending opus-format voice messages to Telegram users
  • Generating multilingual audio in Japanese, Korean, or Spanish
  • Recording WAV or MP3 narration for video or podcast projects
  • Producing roleplay character voices with presets like tsundere or maid

Пример сценария

ВВОД

User asks: 'Say good morning to me in Japanese with a gentle voice'

АГЕНТ
  1. 1

    Translate 'good morning' to Japanese internally: 'おはようございます'

  2. 2

    Select mood 'gentle' to match a warm companion response

  3. 3

    Call tts.py --voice Maia --mood gentle --language Japanese --format mp3

  4. 4

    Receive streaming audio from DashScope WebSocket

  5. 5

    Send tts_output.mp3 and original translated text to user

ВЫВОД

MP3 audio of 'おはようございます' in Maia's gentle voice

Требования

  • DASHSCOPE_API_KEY environment variable
  • Alibaba Cloud account with DashScope (Bailian) API access enabled

Установка

clawhub install yanmoon321/qwen3-tts-instruct

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки