tts

Turn text and subtitles into ready-to-use speech audio.

speech synthesis

What it does

Generates speech audio from text with local or cloud backends, timeline modes, and per-segment voice control.

When to use it

Use for text-to-speech, document narration, voice cloning, dubbing, or time-aligned subtitle audio.

Give it text or source content; it saves generated speech audio to the requested output path.

What you provide

This skill

Noiz

Write

Uploads text and reference audio

reference audio URLs

Read

Downloads remote reference audio

requests

Execute

Installs requests when missing

~/.config/noiz/api_key

Write

Stores your Noiz API key

Python 3 runs the skill's command-line scripts.

ffmpeg must be on PATH when using timeline rendering.

Authenticated Noiz features can use NOIZ_API_KEY from the environment; guest mode works without it.