Перейти к содержимому
TakoAPI
Назад к навыкам

comfyui-tts

от yhsi5358

Git & GitHub
514Число загрузок по данным clawskills.sh
1Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

Generate speech audio using ComfyUI Qwen-TTS service.

Описание

Что делает этот навык

Converts text to speech using ComfyUI's Qwen-TTS service via a shell script. Supports configurable voice characters (Girl, Boy), speaking styles (Emotional, Neutral), and three model sizes (0.5B, 1.7B, 3B). Output is a WAV file saved to ComfyUI's configured output directory.

Runs entirely on a local ComfyUI instance, so there are no per-request cloud API costs or data sent to third-party services.

Когда его использовать

  • Generating voiceover narration for a video project
  • Converting a written article to audio for listening while commuting
  • Creating character voices for an interactive story or game prototype
  • Producing audio prompts for a kiosk or accessibility interface
  • Batch-generating speech samples in Mandarin Chinese for language learning content

Пример сценария

ВВОД

User asks: Generate speech from 'Welcome to the demo' using a calm girl voice and the 1.7B model

АГЕНТ
  1. 1

    Constructs a ComfyUI workflow JSON with the input text, character set to Girl, style set to Neutral, and model set to 1.7B

  2. 2

    Submits the workflow to the local ComfyUI /prompt endpoint

  3. 3

    Polls /history until the job status shows completion

  4. 4

    Retrieves the output file path from the job history response

ВЫВОД

Path to the generated WAV file in ComfyUI's output directory

Требования

  • ComfyUI installed and running locally with the Qwen-TTS model loaded

Установка

clawhub install yhsi5358/comfyui-tts

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

Ссылки