Local Llama TTS

通过 scripts/tts-local.sh 封装 llama-tts 与 OuteTTS-1.0-0.6B GGUF 模型，在本地把输入文本合成为 WAV 音频，可选指定输出文件、说话人参考文件与温度；模型与声码器权重需自行下载并放置到固定目录。

热度 69.37

最近更新 2026-05-17 12:10:07

分类：效率依赖：代码执行 / 读写文件应用场景：文件转换 / 自动化脚本

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add local-llama-tts

Metadata

name: local-llama-tts
description: Local text-to-speech using llama-tts (llama.cpp) and OuteTTS-1.0-0.6B model.
metadata: {"openclaw":{"emoji":"🔊","requires":{"bins":["llama-tts"]}}}

Synthesize speech locally using llama-tts and the OuteTTS-1.0-0.6B model.

You can use the wrapper script:

Location: scripts/tts-local.sh (inside skill folder)
Model: /data/public/machine-learning/models/text-to-speach/OuteTTS-1.0-0.6B-Q4_K_M.gguf
Vocoder: /data/public/machine-learning/models/text-to-speach/WavTokenizer-Large-75-Q4_0.gguf
GPU: Enabled via llama-tts.

Model: Download from OuteAI/OuteTTS-1.0-0.6B-GGUF
Vocoder: Download from ggml-org/WavTokenizer (Note: Felix uses a Q4_0 version, Q5_1 is linked here as a high-quality alternative).

Place files in /data/public/machine-learning/models/text-to-speach/ or update scripts/tts-local.sh.

The model card recommends the following settings (hardcoded in the script):