Documentation Index
Fetch the complete documentation index at: https://mintlify.com/MateoRiosdev/Free-TTS-VozCraft/llms.txt
Use this file to discover all available pages before exploring further.
Customization Options
VozCraft offers extensive customization controls that let you fine-tune every aspect of your generated audio. This guide provides comprehensive documentation of all customization parameters, their technical details, and best practices for achieving optimal results.Customization Overview
VozCraft’s audio is shaped by four main customization axes:Voice Type
2 Options: Normal (0.75 pitch) and High-pitched (1.30 pitch)Controls the base pitch and gender characteristics of the voice
Speed
5 Options: Very Slow to Very Fast (0.50x - 1.60x)Controls how quickly the text is spoken
Mood
8 Options: Neutral, Happy, Serious, and moreControls emotional tone through pitch, rate, and volume
Language
22+ Options: Multiple languages and regional accentsControls pronunciation, accent, and language
Combined Effect: These parameters work together multiplicatively, allowing for thousands of unique voice combinations.
Voice Type (Género de Voz)
Voice Type controls the base pitch and attempts to select appropriate system voices:Normal Voice (Voz Normal) 🔉
- Pitch Multiplier: 0.75 (25% lower than baseline)
- Rate Adjustment: -0.05 (slightly slower)
- Gender Preference: Male voices
- Tone: Deeper, more authoritative
- Voice Search Keywords: “male”, “man”, “guy”, “masculin”, and specific male voice names
- Base frequency:
120 Hz * 0.75 = 90 Hz - Typical range: 80-100 Hz (low male voice)
- Combined with mood pitch:
finalPitch = 0.75 * moodPitch
- Professional content
- Business presentations
- Educational material
- Audiobooks
- Serious topics
- Long-form content
High-pitched Voice (Voz Aguda) 🔊
- Pitch Multiplier: 1.30 (30% higher than baseline)
- Rate Adjustment: +0.05 (slightly faster)
- Gender Preference: Female voices
- Tone: Lighter, more energetic
- Voice Search Keywords: “female”, “woman”, “girl”, “femenin”, and specific female voice names
- Base frequency:
120 Hz * 1.30 = 156 Hz - Typical range: 150-180 Hz (female voice)
- Combined with mood pitch:
finalPitch = 1.30 * moodPitch
- Children’s content
- Marketing and advertising
- Upbeat announcements
- Character voices
- Entertainment content
- Energetic presentations
Voice Type Selection Algorithm
VozCraft intelligently selects system voices:System Dependent: Voice availability depends on your operating system. VozCraft will use the best available voice, but gender matching is not guaranteed on all systems.
Speed (Velocidad) ⚡
Speed controls how fast the text is spoken, measured as a rate multiplier:Speed Options
- Very Slow (Muy Lento)
- Slow (Lento)
- Normal
- Fast (Rápido)
- Very Fast (Muy Rápido)
- Extremely slow, deliberate pace
- Maximum clarity and articulation
- Easy to follow for non-native speakers
- Ideal for learning and note-taking
- 100 characters: ~14 seconds (vs 7 at normal)
- 1000 characters: ~140 seconds (vs 70 at normal)
- Language learning (pronunciation practice)
- Dictation and transcription
- Accessibility (processing difficulties)
- Complex technical content
- Meditation and relaxation
Speed Calculation
Speed combines with voice type and mood:Example: Normal + Neutral
Example: Normal + Neutral
Example: Very Fast + High-pitched + Energetic
Example: Very Fast + High-pitched + Energetic
Example: Very Slow + Normal + Melancholic
Example: Very Slow + Normal + Melancholic
Mood (Estado de Ánimo) 💫
Mood presets modify pitch, rate, and volume to create emotional character:Mood Options
- Neutral 😐
- Happy 😄 (Alegre)
- Serious 😠 (Serio)
- Enthusiastic 🤩 (Entusiasta)
- Melancholic 😔 (Melancólico)
- Energetic ⚡ (Enérgico)
- Relaxed 😌 (Relajado)
- Tense 😤 (Tenso)
- Pitch: 1.00 (baseline)
- Rate: 1.00x (no change)
- Volume: 100%
- Completely neutral emotional tone
- Balanced, professional sound
- No pitch or rate modifications
- Standard reference point
- Normal voice: 0.75 * 1.00 = 0.75
- High-pitched: 1.30 * 1.00 = 1.30
- Professional presentations
- News and journalism
- Technical documentation
- Business communications
- When other moods are too expressive
Mood Visualization
VozCraft displays a visual mood indicator showing the relative values:- Pitch: Scales from 0.70 (Melancholic) to 1.35 (Enthusiastic)
- Rate: Scales from 0.78 (Melancholic) to 1.30 (Energetic)
- Volume: Scales from 0.88 (Melancholic) to 1.00 (multiple moods)
Combining Customizations
Parameter Interaction
All customization parameters work together:Extreme Combinations
Highest Pitch Possible
Settings:Very high, extremely energetic voice (capped at 2.0 by browser)
- Voice Type: High-pitched (1.30)
- Mood: Enthusiastic (1.35)
Lowest Pitch Possible
Settings:Very deep, somber voice
- Voice Type: Normal (0.75)
- Mood: Melancholic (0.70)
Fastest Rate Possible
Settings:Extremely rapid speech
- Speed: Very Fast (1.60)
- Voice Type: High-pitched (+0.05)
- Mood: Energetic (1.30x)
Slowest Rate Possible
Settings:Extremely slow, contemplative pace
- Speed: Very Slow (0.50)
- Voice Type: Normal (-0.05)
- Mood: Melancholic (0.78x)
Recommended Combinations
- Professional Content
- Educational Content
- Marketing Content
- Audiobook/Long-form
- Children's Content
- Meditation/Relaxation
Best for business, presentations, formal contentRecommended:
- Voice: Normal
- Speed: Normal
- Mood: Neutral or Serious
- Language: Match audience
- Pitch: 0.75 (Neutral) or 0.60 (Serious)
- Rate: 0.95 (Neutral) or 0.836 (Serious)
- Volume: 100% (Neutral) or 95% (Serious)
Advanced Customization Tips
Fine-tuning Your Audio
Start with Defaults
Begin with:
- Voice: Normal
- Speed: Normal
- Mood: Neutral
Adjust One Parameter at a Time
Make incremental changes:
- Try High-pitched voice if Normal is too deep
- Adjust speed if pacing feels off
- Finally, select mood for emotional tone
Test with Representative Text
Use actual content, not “test test”:
- Include punctuation (affects pauses)
- Use varied sentence lengths
- Include numbers if relevant
- Test with typical content length
Consider Your Audience
Customize for listeners:
- Native speakers: Normal speed acceptable
- Language learners: Slow or Very Slow
- Elderly: Slower speeds, moderate pitch
- Children: Higher pitch, moderate speed
- Professional: Normal voice, Neutral or Serious
Common Mistakes to Avoid
Language-Specific Considerations
Tonal Languages (Chinese, Vietnamese)
Tonal Languages (Chinese, Vietnamese)
Special Considerations:
- Pitch changes affect meaning in tonal languages
- Stick closer to Neutral mood (1.00 pitch)
- Avoid Enthusiastic (1.35) and Melancholic (0.70) extremes
- Test carefully with native speakers
Syllable-timed Languages (Spanish, Italian)
Syllable-timed Languages (Spanish, Italian)
Special Considerations:
- These languages flow naturally at various speeds
- Speed changes generally well-tolerated
- Mood variations work well
- Natural rhythm preserved at most settings
Stress-timed Languages (English, German)
Stress-timed Languages (English, German)
Special Considerations:
- Extreme speeds can disrupt stress patterns
- Very Fast (1.60) may reduce clarity significantly
- Mood variations generally effective
- Consider slower speeds for non-native learners
Browser Limitations
Web Speech API Constraints
The Web Speech API has built-in limits:- Pitch: 0.1 to 2.0
- Rate: 0.1 to 10.0
- Volume: 0.0 to 1.0
Platform Differences
- Chrome/Edge
- Safari
- Firefox
Characteristics:
- Best overall support
- Smooth parameter transitions
- Good pitch/rate accuracy
- Wide range support
Next Steps
Voice Settings Guide
Step-by-step guide for optimal voice configuration
Using VozCraft
Complete workflow guide with examples
Audio Export
Learn how to export with custom settings
