본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

comfyui-tts

yhsi5358 제작

Git & GitHub
514clawskills.sh가 보고한 다운로드 수
1조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

Generate speech audio using ComfyUI Qwen-TTS service.

설명

이 스킬이 하는 일

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.

사용 시점

  • 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

예시 워크플로

입력

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

에이전트
  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

출력

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

요구 사항

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

설치

clawhub install yhsi5358/comfyui-tts

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크