Ready to supercharge your AI agents?

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

Kokoro TTS — measured AI agent skill | DecimalAI

sundial-org/kokoro-tts

NewSkillScoreMaintained

Generate spoken audio from text using the local Kokoro TTS engine. Use when the user asks to "say" something, requests a voice message, or wants text converted to speech.

design-mediaby sundial-org

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/sundial-org-kokoro-tts/SKILL.md

decimalai skills pull sundial-org-kokoro-tts --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/sundial-org-kokoro-tts/SKILL.md https://app.decimal.ai/s/sundial-org-kokoro-tts/SKILL.md

Raw file: /s/sundial-org-kokoro-tts/SKILL.md ↗ · machine-readable summary at /s/sundial-org-kokoro-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 2h ago

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

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-48%	0%
case-04	✗→✓	▲ Improved	-34%	0%
case-05	✗→✓	▲ Improved	-34%	0%
case-06	✗→✓	▲ Improved	-39%	0%
case-07	✗→✓	▲ Improved	-49%	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

sundial-org / awesome-openclaw-skills

skills/kokoro-tts/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1Bundled 2 files · scripts

Skill contents

scripts/

references/

SKILL.md

Kokoro TTS

This skill allows you to generate high-quality AI speech using a local or remote Kokoro-TTS instance.

Configuration

The skill uses the KOKORO_API_URL environment variable to locate the API.

Default: http://localhost:8880/v1/audio/speech
To Configure: Add KOKORO_API_URL=http://your-server:port/v1/audio/speech to your .env file or environment.

Usage

To generate speech, run the included Node.js script.

Command

bash
node skills/kokoro-tts/scripts/tts.js "<text>" [voice] [speed]

text: The text to speak. Wrap in quotes.
voice: (Optional) The voice ID. Defaults to af_heart.
speed: (Optional) Speech speed (0.25 to 4.0). Defaults to 1.0.

Example

bash
node skills/kokoro-tts/scripts/tts.js "Hello Ed, this is Theosaurus speaking." af_nova

Output

The script will output a single line starting with MEDIA: followed by the path to the generated MP3 file. OpenClaw will automatically pick this up and send it as an audio attachment.

Example Output: MEDIA: media/tts_1706745000000.mp3

Available Voices

Common choices:

af_heart (Default, Female, Warm)
af_nova (Female, Professional)
am_adam (Male, Deep)
bf_alice (British Female)

For a full list, see references/voices.md or query the API.

Want to see if sundial-org/kokoro-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.