본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

qwen3-tts-local-inference

jithinm 제작

DevOps & Cloud
—아직 평가 없음
내 평가

요약

Generate speech from text using Qwen3-TTS via direct Python inference — no server required.

설명

이 스킬이 하는 일

Runs Qwen3-TTS speech synthesis locally via Python with no server or API required. Supports three modes: built-in speakers, natural language voice description, and voice cloning from a short audio clip. Outputs .wav files and works fully offline after the initial model download.

Runs entirely offline after setup, avoiding API rate limits, per-character costs, and data privacy concerns tied to cloud TTS services.

사용 시점

  • Generating voiceovers for video content without cloud costs
  • Cloning a speaker's voice from a 3-second audio clip
  • Producing multilingual audio narration in Chinese, English, Japanese, or Korean
  • Embedding TTS generation directly into a Python data pipeline
  • Quickly prototyping spoken UI with a specific emotional tone or accent

예시 워크플로

입력

User asks: clone my voice from a short recording and read back a script in English

에이전트
  1. 1

    Locate the reference audio file (~3 seconds) and its transcript

  2. 2

    Run tts.py with --mode voice-clone, --ref-audio, --ref-text, and the target text

  3. 3

    Monitor output for the generated .wav file path

  4. 4

    Confirm duration and inference time from the JSON result

출력

A .wav file in tts_output/ spoken in the cloned voice

설치

clawhub install jithinm/qwen3-tts-local-inference

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

링크