AGENT SKILL

sherpa-onnx-tts

Local text-to-speech via sherpa-onnx (offline, no cloud)

License 许可
MIT
所属仓库
openclaw/openclaw
最近更新
2026-11-11
Stars
★ 39w
Forks
8.3w

01 前言 Front Matter

name
sherpa-onnx-tts
metadata
{ "openclaw": { "os": [ "darwin", "linux", "win32" ], "emoji": "?", "install": [ { "id": "download-runtime-macos", "os": [ "darwin" ], "url": "https://github.com/k2-fsa/sherpa-onnx/releases/download/v1.13.8/sherpa-onnx-v1.13.8-osx-universal2-shared.tar.bz2", "kind": "download", "label": "Download sherpa-onnx runtime (macOS)", "sha256": "2249f97f10df7d828af1b0d10e3d1eeaa2198b60b9a999a7ed853c150181ccfd", "archive": "tar.bz2", "extract": true, "targetDir": "runtime", "stripComponents": 1 }, { "id": "download-runtime-linux-x64", "os": [ "linux" ], "url": "https://github.com/k2-fsa/sherpa-onnx/releases/download/v1.13.8/sherpa-onnx-v1.13.8-linux-x64-shared.tar.bz2", "kind": "download", "label": "Download sherpa-onnx runtime (Linux x64)", "sha256": "c0bdb7907d3a74bba1d55d22bf4d9fa75586cf1530614ebe88a27b9118e015c4", "archive": "tar.bz2", "extract": true, "targetDir": "runtime", "stripComponents": 1 }, { "id": "download-runtime-win-x64", "os": [ "win32" ], "url": "https://github.com/k2-fsa/sherpa-onnx/releases/download/v1.13.8/sherpa-onnx-v1.13.8-win-x64-shared-MD-Release.tar.bz2", "kind": "download", "label": "Download sherpa-onnx runtime (Windows x64)", "sha256": "3e971a04b2e0ba4dfa53d381a006367ce8c9f5f09b4ae00043e9845c2baded22", "archive": "tar.bz2", "extract": true, "targetDir": "runtime", "stripComponents": 1 }, { "id": "download-model-lessac", "url": "https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-piper-en_US-lessac-high.tar.bz2", "kind": "download", "label": "Download Piper en_US lessac (high)", "archive": "tar.bz2", "extract": true, "targetDir": "models" } ], "requires": { "env": [ "SHERPA_ONNX_RUNTIME_DIR", "SHERPA_ONNX_MODEL_DIR" ] } } }
description
Local text-to-speech via sherpa-onnx (offline, no cloud)

02 资源文件 1

03 SKILL.md 正文

sherpa-onnx-tts

Local TTS using the sherpa-onnx offline CLI.

Install

  1. Download the runtime for your OS (extracts into $OPENCLAW_STATE_DIR/tools/sherpa-onnx-tts/runtime, default ~/.openclaw/tools/sherpa-onnx-tts/runtime)
  2. Download a voice model (extracts into $OPENCLAW_STATE_DIR/tools/sherpa-onnx-tts/models, default ~/.openclaw/tools/sherpa-onnx-tts/models)

Resolve the active state directory first:

STATE_DIR="${OPENCLAW_STATE_DIR:-$HOME/.openclaw}"

Then write those resolved paths into the active OpenClaw config file ($OPENCLAW_CONFIG_PATH, default ~/.openclaw/openclaw.json):

{
  skills: {
    entries: {
      "sherpa-onnx-tts": {
        env: {
          SHERPA_ONNX_RUNTIME_DIR: "/path/to/your/state-dir/tools/sherpa-onnx-tts/runtime",
          SHERPA_ONNX_MODEL_DIR: "/path/to/your/state-dir/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:

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

Usage

{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."

04 同仓库更多 Skills