$ loading_
Convert text to speech locally and offline with sherpa-onnx, no cloud needed.
The materials indicate this is a local offline TTS wrapper with no required secrets and no declared remote endpoints, so the overall risk appears low. Caution is still warranted because it invokes a local CLI, reads local model files, and writes audio output, which are normal capabilities for this type of local tool.
The materials explicitly state that no keys are required and no sensitive tokens are mentioned in environment variables; configuration only covers local runtime and model directory paths, with no evident credential exposure or abuse surface.
The description states offline and no cloud, and the system checks indicate no remote endpoint host; based on the materials, there is no declared transmission of user text or audio to external services.
This skill runs a local sherpa-onnx CLI/Node wrapper and allows invoking a local binary through PATH, arguments, and environment variables; this is a normal execution capability for a local tool, and no excessive system permission request is evident in the materials.
The skill needs to read local runtime/model directories and writes output to a user-specified file such as ./tts.wav; it also allows overriding model, tokens, and data directories via arguments. This is local file access consistent with TTS functionality, with no clearly excessive access described.
The source is an open-source GitHub repository with very high community adoption (about 377k stars), which are strong risk-reducing signals; however, the license is not stated, maintenance status is unknown, and installation depends on manually downloading the runtime and voice model, so verifying download sources and version integrity is advisable.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "sherpa-onnx-tts" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/skills/sherpa-onnx-tts/SKILL.md 2. Save it as ~/.claude/skills/sherpa-onnx-tts/SKILL.md 3. Reload skills and tell me it's ready
Use sherpa-onnx-tts to convert the following English text into natural speech, save it as a WAV file, and keep the pace moderate and pronunciation clear: Welcome to our product demo. In the next few minutes, I will walk you through the core features.
A locally generated narration audio file suitable for demos, introductions, or voiceovers.
Use sherpa-onnx-tts to turn this study note into speech for offline listening, with natural pauses between clauses: Overfitting in machine learning happens when a model performs well on training data but generalizes poorly to new data.
A clear spoken study audio file for offline listening during commuting or review.
Use sherpa-onnx-tts to generate separate audio files for these three prompts, with consistent volume and speaking rate: First, the meeting will begin in ten minutes. Second, please remember to save your current work. Third, the system update has been completed.
Multiple separate local voice prompt files suitable for notifications, announcements, or automation.
Local TTS using the sherpa-onnx offline CLI.
$OPENCLAW_STATE_DIR/tools/sherpa-onnx-tts/runtime, default ~/.openclaw/tools/sherpa-onnx-tts/runtime)$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"
{baseDir}/bin/sherpa-onnx-tts -o ./tts.wav "Hello from local TTS."
Notes:
tts-models release if you want another voice..onnx files, set SHERPA_ONNX_MODEL_FILE or pass --model-file.--tokens-file or --data-dir to override the defaults.node {baseDir}\\bin\\sherpa-onnx-tts -o tts.wav "Hello from local TTS."Verify an OpenClaw release is fully published and working across all channels.
Fetch GitHub issues, create fixes, open PRs, and handle reviews.
Regenerate OpenClaw release changelog sections from Git history before releases.
Prepare and verify OpenClaw stable or beta releases and release notes.
Automate web page workflows, login checks, tab handling, and recovery steps.
Create and review technical docs and agent instruction files in repositories.
Transcribe audio to text locally with Whisper CLI, no API key required.
Convert text into multilingual speech and save it as MP3 audio.
Convert text to speech quickly and browse available voices and models.
Convert text into voiceovers, accessibility reads, and batch audio prompts.
Enable low-latency local speech synthesis and playback control for AI agents.
Add text-to-speech and speech-to-text workflows to apps via REST or MCP.