$npx -y skills add SafeAI-Lab-X/ClawKeeper --skill sherpa-onnx-ttsLocal text-to-speech via sherpa-onnx (offline, no cloud)
| 1 | # sherpa-onnx-tts |
| 2 | |
| 3 | Local TTS using the sherpa-onnx offline CLI. |
| 4 | |
| 5 | ## Install |
| 6 | |
| 7 | 1. Download the runtime for your OS (extracts into `~/.openclaw/tools/sherpa-onnx-tts/runtime`) |
| 8 | 2. Download a voice model (extracts into `~/.openclaw/tools/sherpa-onnx-tts/models`) |
| 9 | |
| 10 | Update `~/.openclaw/openclaw.json`: |
| 11 | |
| 12 | ```json5 |
| 13 | { |
| 14 | skills: { |
| 15 | entries: { |
| 16 | "sherpa-onnx-tts": { |
| 17 | env: { |
| 18 | SHERPA_ONNX_RUNTIME_DIR: "~/.openclaw/tools/sherpa-onnx-tts/runtime", |
| 19 | SHERPA_ONNX_MODEL_DIR: "~/.openclaw/tools/sherpa-onnx-tts/models/vits-piper-en_US-lessac-high", |
| 20 | }, |
| 21 | }, |
| 22 | }, |
| 23 | }, |
| 24 | } |
| 25 | ``` |
| 26 | |
| 27 | The wrapper lives in this skill folder. Run it directly, or add the wrapper to PATH: |
| 28 | |
| 29 | ```bash |
| 30 | export PATH="{baseDir}/bin:$PATH" |
| 31 | ``` |
| 32 | |
| 33 | ## Usage |
| 34 | |
| 35 | ```bash |
| 36 | {baseDir}/bin/sherpa-onnx-tts -o ./tts.wav "Hello from local TTS." |
| 37 | ``` |
| 38 | |
| 39 | Notes: |
| 40 | |
| 41 | - Pick a different model from the sherpa-onnx `tts-models` release if you want another voice. |
| 42 | - If the model dir has multiple `.onnx` files, set `SHERPA_ONNX_MODEL_FILE` or pass `--model-file`. |
| 43 | - You can also pass `--tokens-file` or `--data-dir` to override the defaults. |
| 44 | - Windows: run `node {baseDir}\\bin\\sherpa-onnx-tts -o tts.wav "Hello from local TTS."` |