Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sundial-org/kokoro-tts
Generate spoken audio from text using the local Kokoro TTS engine.
Passed 16 of 19 test cases with the skill, and 4 of 19 without it.
and 15 more in the full report
15 fixed4 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need to generate a voice clip for the message 'System update complete'. I have not set any custom voice or speed flags and want to rely on the default voice setup. What is the CLI command?
| Checked | Without skill | With skill |
|---|---|---|
| Executes node skills/kokoro-tts/scripts/tts.js | Missed | Passed |
| Passes 'System update complete' as the text argument | Missed | Passed |
The instructions your model reads when the skill loads.
This skill allows you to generate high-quality AI speech using a local or remote Kokoro-TTS instance.
The skill uses the KOKORO_API_URL environment variable to locate the API.
http://localhost:8880/v1/audio/speechKOKORO_API_URL=http://your-server:port/v1/audio/speech to your .env file or environment.To generate speech, run the included Node.js script.
node skills/kokoro-tts/scripts/tts.js "<text>" [voice] [speed]
af_heart.1.0.node skills/kokoro-tts/scripts/tts.js "Hello Ed, this is Theosaurus speaking." af_nova
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
test cases passed, vs 4 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.