agentleFS
foxl-aifoxl-ai/skills/skills/sherpa-onnx-tts/SKILL.md

sherpa-onnx-tts

Skill0 starsChanged 32 days agoMIT-0View on GitHub

Offline text-to-speech with sherpa-onnx: turn text into a WAV file on this computer, no cloud or API key. Use when the user wants text read aloud or saved as speech audio locally.

  • Installs packages

33 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use taskflow-inbox-triage, node-connect and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AtomicBot-aiSkill

    taskflow-inbox-triage

    Also in 6 projects that use this

  • hkyutongSkill

    node-connect

    Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale, or plugins.entries.device-pair.config.publicUrl.

    Also in 18 projects that use this

  • molt-botSkill

    discord-e2e

    Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and Gateway evidence from manual user interactions.

    Also in 10 projects that use this

  • molt-botSkill

    openclaw-repair-sweep

    Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.

    Also in 10 projects that use this

  • clawdbotSkill

    openclaw-performance

    Performance work in OpenClaw: a slow or heavy flow (latency, CPU, memory, SQL, RPC, renders), writing or reviewing a perf PR, or adding a cache. Count the work, delete waste first, cache last.

    Also in 7 projects that use this

  • clawdbotSkill

    plugin-sdk-impact

    Count Plugin SDK consumers across live ClawHub releases and bundled OpenClaw plugins before deprecation, removal, or behavior changes; supports public release-date filters.

    Also in 7 projects that use this

  • +2 more from molt-bot

The file

Files
SKILL.md

sherpa-onnx TTS (offline)

Runs sherpa-onnx-offline-tts with a downloaded voice model. Source: https://github.com/k2-fsa/sherpa-onnx (models: release tag tts-models).

  • SHERPA_ONNX_RUNTIME_DIR - a folder whose bin/ (Windows: Scripts\) holds sherpa-onnx-offline-tts
  • SHERPA_ONNX_MODEL_DIR - an extracted VITS/Piper voice folder (*.onnx, tokens.txt, espeak-ng-data/)

Both can be saved on the Integrations page; Foxl passes them to exec.

Setup (once)

Runtime in its own virtualenv (pip package sherpa-onnx-bin carries the binaries):

python3 -m venv ~/.foxl/tools/sherpa-onnx-tts/runtime
~/.foxl/tools/sherpa-onnx-tts/runtime/bin/pip install sherpa-onnx-bin

Voice (about 65 MB; other voices: same URL with another name from the tts-models release, e.g. vits-piper-en_US-ryan-medium, vits-piper-de_DE-thorsten-medium):

mkdir -p ~/.foxl/tools/sherpa-onnx-tts/models && cd ~/.foxl/tools/sherpa-onnx-tts/models
curl -LO https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-piper-en_US-lessac-medium.tar.bz2
tar xf vits-piper-en_US-lessac-medium.tar.bz2 && rm vits-piper-en_US-lessac-medium.tar.bz2

Then set SHERPA_ONNX_RUNTIME_DIR=~/.foxl/tools/sherpa-onnx-tts/runtime and SHERPA_ONNX_MODEL_DIR=~/.foxl/tools/sherpa-onnx-tts/models/vits-piper-en_US-lessac-medium (use absolute paths).

Speak

M="$SHERPA_ONNX_MODEL_DIR"
"$SHERPA_ONNX_RUNTIME_DIR/bin/sherpa-onnx-offline-tts" \
  --vits-model="$(ls "$M"/*.onnx | head -1)" \
  --vits-tokens="$M/tokens.txt" \
  --vits-data-dir="$M/espeak-ng-data" \
  --num-threads=2 \
  --output-filename=./speech.wav \
  "Hello from local text to speech."

Optional: --speed=1.2 (faster), --sid=<n> (speaker id for multi-speaker models). Play only if the user asked: afplay speech.wav (macOS), aplay speech.wav (Linux), (New-Object Media.SoundPlayer 'speech.wav').PlaySync() (Windows PowerShell).

Notes

  • Kokoro, Matcha and other model families take different flags (--kokoro-model, ...); run sherpa-onnx-offline-tts --help and read the model's folder.
  • Very long text: split into paragraphs and synthesize each, so one call stays well under the exec timeout.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.