Skip to content
Eli Lab edited this page Mar 2, 2026 · 2 revisions

FAQ

Frequently Asked Questions about Hiro UST Generator.

General Questions

What is Hiro UST Generator?

Hiro UST Generator is a tool that automatically creates UST/USTX files (used in UTAU voice synthesis) from Japanese lyrics. It handles:

  • Automatic phonemization of Japanese text
  • Intelligent melody generation
  • Voice-specific pitch ranges
  • Accent pattern support
  • Fine-tuned parameter adjustment

Do I need to know music theory?

No! The default settings work well for most cases. The tool handles:

  • Scale selection
  • Pitch range assignment
  • Note duration calculation
  • Accent pattern application

Just enter your lyrics and click Generate!

Can I use it with languages other than Japanese?

Currently, Japanese is the primary language. Romaji input is supported (e.g., "kyakkya" for "きゃっきゃ").

Is it free?

[Check your license terms]

Q: Which platforms are supported?

A: Windows only currently. macOS and Linux support coming in future versions.

Q: What synthesizer should I use?

A: OpenUtau (recommended) for best results. Avoids character encoding issues with UTAU.


Installation & Setup

Q: How do I install it?

A: See Installation guide.

Q: Do I need Python installed?

A: Yes, Python 3.8 or higher. Download from python.org

Q: Can I use it on Mac/Linux?

A: Yes! It works on Windows, macOS, and Linux.

Q: How much disk space do I need?

A: About 100 MB for the application and dependencies.


Usage Questions

Q: How do I enter lyrics?

A: In the "🎵 Song Lyrics" section, type Japanese text:

[Verse 1]
きゃっきゃ うれし

[Chorus]
いたみ いたみ

You can use:

  • Hiragana: あいうえお
  • Katakana: アイウエオ
  • Romaji: a i u e o

Q: What does "Seed" do?

A: It controls randomness. The same seed always produces the same melody.

Use the 🎲 button to try different melodies with one click.

Q: How do I get different melodies?

A: Multiple options:

  1. Change Seed: Click 🎲 Randomize button
  2. Change Scale: Try different musical scales
  3. Change Accent: Different accent patterns = different melodies
  4. Adjust Curve: Bias melody up or down
  5. Disable Motif: Turn off "Motif Memory" for more variety

Q: What's the difference between Voice and Scale?

A:

  • Voice (Soprano/Alto/Tenor/Bass): Sets the key range (high/low)
  • Scale (Major/Minor/Pentatonic): Determines which notes can be used

Q: How do I save my settings?

A: Click "💾 Save Preset" to save current settings. Load them later with "📂 Load Preset"

Q: Can I undo changes?

A: Not in the current version. Settings are live, so adjust and preview before generating.


Output & Compatibility

Q: What's the difference between UST and USTX?

A:

Format Best For Stability
UST UTAU (Windows) ⚠️ Has character encoding issues
USTX OpenUtau (all platforms) ✅ Stable (recommended)

Q: Which should I use?

A: Use USTX + OpenUtau for best results. UST in UTAU sometimes produces Chinese characters.

Q: Can I use this with other synthesizers?

A: Only with UTAU/OpenUtau which support UST format. OpenUtau recommended for stability.


Melody & Accents

Q: What are accent patterns?

A: Japanese pitch patterns that make words sound natural:

  • Heiban: Flat tone
  • Atamadaka: High → Low
  • Nakadaka: Low → High → Low
  • Odaka: Low → High

Setting the correct accent makes lyrics sound more natural.

Q: How do I know which accent to use?

A: Generally:

  • Greetings: Atamadaka
  • Common words: Heiban or Atamadaka
  • Polite speech: Nakadaka
  • Formal: Odaka

Use preview to test!

Q: What's "Motif Memory"?

A: It remembers pitch patterns from previous notes and continues them, making melodies more coherent and less random.

Q: What's "Lyrical Mode"?

A: It generates intelligent melodies based on:

  • Text structure
  • Phoneme characteristics
  • Voice range
  • Musical scale

Sounds more natural than pure random selection.


Parameters

Q: What does "Pre-Utterance" do?

A: It's the lead-in time (in milliseconds) before a note starts. Adjust for smoother transitions between notes.

Typical values: 20-40ms

Q: What's "Voice Overlap"?

A: How much the current note overlaps with the previous one. Creates smoother legato transitions.

Typical values: 5-15ms

Q: What's "Intensity"?

A: Volume level of the note.

Range: 0-200 Typical: 80

Q: What's "Envelope"?

A: The pitch envelope preset that affects how the note sounds:

  • Pop: Balanced
  • Opera: Sustained
  • Whisper: Soft
  • Belt: Powerful

Experiment to find your preference!

Q: How do I adjust note lengths?

A: Use "Length Variation" (0.0 = fixed, 1.0 = maximum randomness) and "Base Length" (default 240 ticks).


Phonemes

Q: What's phoneme mode?

A: How the tool represents sounds:

  • Japanese: Uses Japanese phonetic system
  • Hepburn: Romanization system
  • Wapuro: Keyboard input romanization
  • English: English phonetic system

Most users should use Japanese mode.

Q: Can I preview phonemes?

A: Yes, click "👀 Preview Phonemes" to hear individual sounds.

Q: What's a mora?

A: The basic unit of sound in Japanese. Examples:

  • "あ" = 1 mora
  • "きゃ" = 1 mora
  • "きゃっきゃ" = 3 moras (きゃ + っ + きゃ)

Troubleshooting

Q: The app crashes on startup

A: Check:

  1. Python 3.8+ is installed
  2. All dependencies installed (pip install -r requirements.txt)
  3. Tkinter is available on your system
  4. Try the command line test in Installation

Q: Generated file is blank/corrupt

A: Try:

  1. Click "Gen" again
  2. Choose different settings
  3. Save to different location
  4. Check disk space

Q: Preview doesn't work

A: Check:

  1. Lyrics are valid Japanese
  2. Phoneme mode is set correctly (use Japanese)
  3. System audio is working
  4. Try a different preview text

Q: Settings reset every time I open the app

A: Save your settings as a preset:

  1. Configure all parameters
  2. Click "💾 Save Preset"
  3. Name your preset
  4. Load it next time with "📂 Load Preset"

Q: Generated melody sounds bad

A: Try different settings:

Problem Solution
Too random Enable "Motif Memory"
Too robotic Enable "Lyrical Mode"
Wrong scale Change "Scale" setting
Wrong key Change "Voice" setting
No emotion Enable "Vibrato" envelope

Performance

Q: How long does generation take?

A: Usually 1-5 seconds for a typical song. Depends on:

  • Number of notes
  • Computer speed
  • Complexity of settings

Q: Why is it slow sometimes?

A: Check:

  1. Disable "Lyrical Mode" for faster generation
  2. Disable "Motif Memory"
  3. Use simpler scale (pentatonic vs chromatic)
  4. Close other applications

Q: Can I batch process multiple files?

A: Not in the current GUI version. CLI interface coming soon.


Compatibility

Q: Which UTAU versions does it support?

A: Works with UTAU 2008+ and OpenUtau (all versions).

Q: Can I use it with VOCALOID?

A: No, VOCALOID has its own file format (VSQx). Use UTAU or OpenUtau.

Q: Does it work with voice banks?

A: Generates UST files compatible with any voice bank. You assign the bank in UTAU after generation.


Getting Help

Still have questions?

Wiki Navigation

⚠️ Windows Only • Best with OpenUtau

📖 User Guide

🔍 Reference


Need help?FAQ
Ready to use?User Guide

Clone this wiki locally