본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

lb-pocket-tts-skill

leonaaardob 제작

Media & Streaming
729clawskills.sh가 보고한 다운로드 수
0조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

Generate speech from text using Kyutai Pocket TTS - lightweight, CPU-friendly, streaming TTS with voice cloning.

설명

이 스킬이 하는 일

Pocket-TTS generates speech from text using the Kyutai model locally on CPU, with no GPU required. It supports voice cloning from short audio samples and streaming output with under 200ms latency. English only, approximately 6x faster than real-time on modern hardware.

Runs entirely on CPU without cloud API dependencies, making it faster to set up and cheaper to operate than hosted TTS services for local or offline workflows.

사용 시점

  • Narrating documentation without a cloud TTS subscription
  • Cloning a custom voice for consistent audio branding
  • Generating speech offline on a laptop during travel
  • Prototyping voice interfaces without API rate limits
  • Batch-converting written content to audio files

예시 워크플로

입력

User asks: generate speech from a script using my own voice sample

에이전트
  1. 1

    Export voice embedding from audio sample with pocket-tts export-voice voice.wav voice.safetensors

  2. 2

    Load the TTSModel and retrieve voice state from the safetensors file

  3. 3

    Call model.generate_audio with the voice state and input text

  4. 4

    Save the returned audio array as a 24kHz WAV file using scipy

출력

A 24kHz mono WAV file with speech in the cloned voice

요구 사항

  • HuggingFace account (to access kyutai/tts-voices or kyutai/pocket-tts model weights)

설치

clawhub install leonaaardob/lb-pocket-tts-skill

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

링크