Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

sherpa-onnx-tts — measured AI agent skill | DecimalAI

understudy-ai/sherpa-onnx-tts

NewSkillScoreMaintained

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

design-mediaby understudy-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/understudy-ai-sherpa-onnx-tts/SKILL.md

decimalai skills pull understudy-ai-sherpa-onnx-tts --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/understudy-ai-sherpa-onnx-tts/SKILL.md https://app.decimal.ai/s/understudy-ai-sherpa-onnx-tts/SKILL.md

Raw file: /s/understudy-ai-sherpa-onnx-tts/SKILL.md ↗ · machine-readable summary at /s/understudy-ai-sherpa-onnx-tts.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago

—-39% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	-47%	0%
case-04	✗→✓	▲ Improved	-63%	0%
case-05	✗→✓	▲ Improved	-60%	0%
case-10	✗→✓	▲ Improved	-16%	0%
case-06	✗→✓	▲ Improved	-69%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

understudy-ai / understudy

skills/sherpa-onnx-tts/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

sherpa-onnx-tts

Local TTS using the sherpa-onnx offline CLI.

Install

Download the runtime for your OS (extracts into ~/.understudy/tools/sherpa-onnx-tts/runtime)
Download a voice model (extracts into ~/.understudy/tools/sherpa-onnx-tts/models)

Update ~/.understudy/config.json5:

json5
{
  skills: {
    entries: {
      "sherpa-onnx-tts": {
        env: {
          SHERPA_ONNX_RUNTIME_DIR: "~/.understudy/tools/sherpa-onnx-tts/runtime",
          SHERPA_ONNX_MODEL_DIR: "~/.understudy/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"

Usage

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."

Want to see if understudy-ai/sherpa-onnx-tts would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.