Just Say It!

Introduction

Just Say It! is an instrument plug-in: it produces audio on its outputs without requiring an audio input. Type or paste text, choose a system voice, press Play, and hear synthesized speech through your mixer.

No AI voices. Just Say It! does not use artificial intelligence for speech. It uses the text-to-speech voices built into your operating system — macOS Speech on Mac and Windows Speech (WinRT, with SAPI fallback) on Windows. The same message appears in the in-plug-in ? help overlay.

Quick Start

1. Install the plug-in for your platform (macOS / Windows) and rescan plug-ins in your DAW.
2. Insert Just Say It! on an instrument or MIDI track.
3. Type text in the main text area (or use the default sample text).
4. Select a voice from the Voice knob or the voice combo list.
5. Click Play — synthesis runs in the background; audio plays when ready.
6. Adjust Speed, Pitch, and Volume while audio is playing.
7. Optional: click Export .wav to save the current text as a mono WAV file.

Tip. Enable Re-trigger (default ON) if you want voice changes or MIDI notes to restart speech immediately while playback is active.

Installation — macOS

System requirement: macOS 10.14 or later, Apple Silicon or Intel.

1. Quit your DAW.
2. Run the installer (.pkg).
3. Rescan plug-ins in your host.
4. If macOS blocks the app, right-click → Open, or allow in System Settings → Privacy & Security.

User data folder. Settings and support files are stored at:
macOS: ~/Library/Application Support/Celestial Textures/Just Say It!
Windows: %ProgramData%\Celestial Textures\Just Say It!

Installation — Windows

System requirement: Windows 10 or later, 64-bit.

1. Close your DAW.
2. Run the setup program.
3. Rescan plug-ins in your host.
4. HTML manual (after installer): %ProgramData%\Celestial Textures\Just Say It!\manual\index.html

The Standalone Application

The standalone app runs Just Say It! without a DAW. Use File → Preferences to choose audio output and MIDI devices.

• macOS: Just Say It! (About, Preferences, Quit) · Window · Help (About, Manual)
• Windows: File (Preferences, Quit) · Help (About, Manual)
• Manual opens the installed HTML manual in your browser when present; otherwise the online manual
• Instrument output only — no audio input is required.

Window Overview

Default window size is 600 × 360 pixels. Drag the corner resizer to scale the UI; the scale is saved in your project or standalone session.

Controls

Speech engine. This plug-in does not use AI. On macOS, speech is rendered with the system say command; on Windows, it uses WinRT Speech (with SAPI fallback). Both use voices already installed on your computer. Pitch and volume knobs apply during playback, not at synthesis time.

Export .wav

The blue Export .wav button sits in the center of the plug-in window, next to Play and Stop. It is available in all plug-in formats (VST3, AU, CLAP, …) and in the standalone application.

1. Type or paste your text and choose a voice (and optional Speed setting).
2. Click Export .wav.
3. Wait while the status line shows Synthesizing for export….
4. Choose a save location in the file dialog — a mono 16-bit WAV is written to disk.

Notes. Export uses the current text and voice settings. Any active playback or synthesis is stopped first. If the text is empty or no valid voice is selected, the status line shows an error instead of opening the save dialog.

Re-trigger

The circular Re-trigger toggle (default ON) controls whether active speech restarts when you change voice or receive MIDI. The knob highlights on mouse-over (same accent as other controls).

Help overlay

Click the ? button in the top-right corner to open the help overlay. Dismiss it by clicking ? again.

At the top of the overlay:

Just Say It!

This plug-in does not use AI for speech.
It uses the text-to-speech voices built into your operating system.

Below that you will find a quick MIDI reference and credits.

MIDI

Any Note On (velocity > 0) can trigger Play according to the Re-trigger rules above.

• C3 (MIDI note 48) = 0 semitones (unity pitch).
• Pitch semitones = note number − 48, clamped to −48 … +48.
• Valid note range for pitch mapping: MIDI notes 0–96.

See also the help overlay for the same MIDI summary inside the plug-in.

Workflows & Tips

• DAW automation — Automate Speed, Pitch, Volume, and Voice index from your host.
• Long text — Very long passages take longer to synthesize; watch the status line.
• Quick stop — Stop cancels synthesis and clears playback immediately.
• Export to disk — Export .wav synthesizes the current text and prompts for a save location. Playback stops while export runs.
• UI scale — Use the corner resizer; scale is recalled when you reload the project.
• Multiple instances — Each instance has its own text and voice selection.

Troubleshooting / FAQ

Does this plug-in use AI voices?

• No. Speech is generated with your operating system's built-in text-to-speech — not cloud or AI models.
• On macOS, voices come from System Settings → Accessibility → Spoken Content (or legacy Speech settings).
• On Windows, install voices under Settings → Time & Language → Speech.

No sound after Play?

• Check that text is not empty and a valid voice is selected.
• On macOS, confirm /usr/bin/say works in Terminal.
• On Windows, verify voices under Settings → Time & Language → Speech (WinRT / OneCore voices).
• Ensure the track is not muted and the plug-in output is routed correctly.

Standalone app: no audio?

• Open Preferences and select a valid output device.

Host does not list the plug-in?

• Confirm install path and rescan / clear plug-in cache.
• Quit and restart the host after installing.

Speech sounds wrong speed?

• Speed affects both synthesis rate and playback; try values near 1.0× first.

Specifications

Credits

Just Say It! version 1.0.0
© 2026 Celestial Textures
Programming by Orestis
www.celestialtextures.com