local-llama-tts
wuxxin 제작
AI & LLMs요약
Local text-to-speech using llama-tts (llama.cpp) and OuteTTS-1.0-0.6B model.
설명
이 스킬이 하는 일
Runs text-to-speech synthesis entirely on local hardware using llama.cpp and the OuteTTS-1.0-0.6B model. Produces WAV audio files from text input with optional speaker reference for voice cloning. No network calls or external APIs involved.
Runs fully offline with GPU acceleration, so there are no API costs, rate limits, or data privacy concerns compared to cloud TTS services.
사용 시점
- Converting notes or documents to audio for offline listening
- Generating voiceovers for local video projects
- Testing TTS output with different speaker reference files
- Batch-producing spoken audio from script text
- Running speech synthesis on air-gapped machines
예시 워크플로
User asks: convert this paragraph to speech and save it as narration.wav
- 1
Receives the text and target filename
- 2
Calls scripts/tts-local.sh with the text and -o narration.wav
- 3
llama-tts loads OuteTTS-1.0-0.6B-Q4_K_M.gguf and WavTokenizer models from local paths
- 4
Synthesizes audio using configured sampling parameters (temp 0.4, top-p 0.9, rep penalty 1.1)
- 5
Writes the result to narration.wav
narration.wav file containing synthesized speech
요구 사항
- llama-tts binary installed and available in PATH
- OuteTTS-1.0-0.6B-Q4_K_M.gguf model file downloaded from HuggingFace (OuteAI/OuteTTS-1.0-0.6B-GGUF)
- WavTokenizer GGUF vocoder model downloaded from HuggingFace (ggml-org/WavTokenizer)
설치
clawhub install wuxxin/local-llama-ttsCLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.