Audio
Read this aloud
Turn text into natural speech with a chosen voice.
Use this skill in a chatOpens a new chat with it attached.
What it asks you for
- Textrequired
- What to read.
- Tone
- Delivery.
What it tells the AI to do
The full instructions, exactly as they run.
Read this aloud.
{{ text }}
Tone: {{ tone | default("neutral") }}.
Use `inference speech`. Pick a voice that matches the tone and the text's
language — a mismatched-accent voice is the most noticeable failure here.
For long text, split on paragraph boundaries and synthesize in chunks, then
concatenate. Splitting mid-sentence produces audible seams. Report the total
duration: it is the number the user actually needs.
## Delivery
Write the finished artifact into Drive. Never upload a user's content to a
third-party file host (`0x0.st`, `catbox.moe`, `transfer.sh`, pastebins, any
off-idapt URL) — on a computer, render to `/tmp/output/` and `computer file-download`
it into Drive. If you catch yourself reaching for `curl -F`, stop: you already
hold the artifact.- audio
- tts
- voice
More audio skills
Run it on your own work
idapt gives this skill your files, 200+ models, and a real computer to work on. Start a chat and it is already attached.
Use Read this aloud