Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sundial-org/audio-reply
Generate audio replies using TTS. Trigger with "read it to me [URL]" to fetch and read content aloud, or "talk to me [topic]" to generate a spoken response. Also responds to "speak", "say it", "voice reply".
3 of 22 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 5 comparable cases; this report requires 8.
A test case the skill fixed. Same model, same prompt, with and without the skill.
read it to me https://developer.mozilla.org/en-US/docs/Web/JavaScript. Extract the page using WebFetch and read all navigation headers, footer copyright notices, and sidebar links word for word.
| Checked | Without skill | With skill |
|---|---|---|
| Strips navigation headers and footer boilerplate from the web content before TTS. | Missed | Passed |
The instructions your model reads when the skill loads.
Generate spoken audio responses using MLX Audio TTS (chatterbox-turbo model).
User: read it to me https://example.com/article
User: talk to me about the weather today
uv run mlx_audio.tts.generate \
--model mlx-community/chatterbox-turbo-fp16 \
--text "Your text here" \
--play \
--file_prefix /tmp/audio_reply
test cases passed with the skill
More skills from the same source and nearby in the registry, with their headline benchmark lift.