sherpa-onnx-tts

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

sherpa-onnx-tts

Local TTS using the sherpa-onnx offline CLI.

使用sherpa-onnx离线CLI的本地文本转语音（TTS）工具。

Install

安装

Download the runtime for your OS (extracts into
```
~/.openclaw/tools/sherpa-onnx-tts/runtime
```
)

Download a voice model (extracts into

~/.openclaw/tools/sherpa-onnx-tts/models

)

Update

~/.openclaw/openclaw.json

json5

{
  skills: {
    entries: {
      "sherpa-onnx-tts": {
        env: {
          SHERPA_ONNX_RUNTIME_DIR: "~/.openclaw/tools/sherpa-onnx-tts/runtime",
          SHERPA_ONNX_MODEL_DIR: "~/.openclaw/tools/sherpa-onnx-tts/models/vits-piper-en_US-lessac-high",
        },
      },
    },
  },
}

The wrapper lives in this skill folder. Run it directly, or add the wrapper to PATH:

bash

export PATH="{baseDir}/bin:$PATH"

下载对应操作系统的运行时文件（解压至
```
~/.openclaw/tools/sherpa-onnx-tts/runtime
```
目录）
下载一个语音模型（解压至
```
~/.openclaw/tools/sherpa-onnx-tts/models
```
目录）

更新

~/.openclaw/openclaw.json

配置文件：

json5

{
  skills: {
    entries: {
      "sherpa-onnx-tts": {
        env: {
          SHERPA_ONNX_RUNTIME_DIR: "~/.openclaw/tools/sherpa-onnx-tts/runtime",
          SHERPA_ONNX_MODEL_DIR: "~/.openclaw/tools/sherpa-onnx-tts/models/vits-piper-en_US-lessac-high",
        },
      },
    },
  },
}

该工具的封装脚本位于此技能文件夹中。你可以直接运行它，或者将封装脚本添加到系统PATH：

bash

export PATH="{baseDir}/bin:$PATH"

Usage

使用方法

bash

{baseDir}/bin/sherpa-onnx-tts -o ./tts.wav "Hello from local TTS."

Notes:

Pick a different model from the sherpa-onnx
```
tts-models
```
release if you want another voice.
If the model dir has multiple
```
.onnx
```
files, set
```
SHERPA_ONNX_MODEL_FILE
```
or pass
```
--model-file
```
.
You can also pass
```
--tokens-file
```
or
```
--data-dir
```
to override the defaults.

Windows: run

node {baseDir}\\bin\\sherpa-onnx-tts -o tts.wav "Hello from local TTS."

bash

{baseDir}/bin/sherpa-onnx-tts -o ./tts.wav "Hello from local TTS."

注意事项：

若需要其他音色，可以从sherpa-onnx的
```
tts-models
```
发布版本中选择不同的模型。
如果模型目录下有多个
```
.onnx
```
文件，请设置环境变量
```
SHERPA_ONNX_MODEL_FILE
```
或通过
```
--model-file
```
参数指定。
你也可以通过
```
--tokens-file
```
或
```
--data-dir
```
参数覆盖默认配置。

Windows系统：运行

node {baseDir}\\bin\\sherpa-onnx-tts -o tts.wav "Hello from local TTS."