text-to-speech
inference-sh6 installs
Turn your text into expressive spoken audio.
What it does
Creates spoken audio from text using models accessed through inference.sh.
When to use it
Use for voiceovers, audiobooks, podcasts, accessibility audio, phone prompts, video narration, and character voices.
How to use it
Give it text to speak; it generates speech and returns an audio URL.
What you provide
- the text to speak
Uses
Good to know
- edits its own instructions
Latest review
What you need · 3
Requires the inference.sh CLI.
Requires an inference.sh account to complete the login step before generating speech.
Access · 2
This skill
inference.sh
Execute
Starts hosted speech generation
Write
Sends text for speech generation
npx skills add belt-sh/cli
Execute
Installs the belt CLI skill