- 1.Speaking Speed: Adjust from 0.5x (slow) to 2.0x (fast). Use slower speeds for learning content, faster for energetic commercials. Default is 1.0x (natural pace)
- 2.Pitch Adjustment: Shift pitch up or down by ±12 semitones. Make voices deeper or higher while maintaining natural quality. Useful for matching specific character tones
- 3.Emotion Control: Set emotional tone from neutral to expressive. Options include: happy, sad, angry, excited, calm, fearful, surprised. Intensity can be adjusted from subtle to pronounced
- 4.Emphasis & Pauses: Use SSML tags in your text: <emphasis>important word</emphasis>, <break time="1s"/> for pauses, <prosody rate="slow">slower section</prosody>
- 5.Pronunciation: Add custom pronunciations for names, technical terms, or brand names. Use phonetic spelling or IPA notation
- 6.Breath & Delivery: Control natural breathing pauses, hesitations, and vocal inflections for more human-like delivery
- 7.Stability vs Variety: Higher stability = consistent delivery. Lower stability = more expressive variation. Adjust based on content type
- 8.To adjust parameters: Open voice generation settings → Click "Advanced Controls" → Modify desired parameters → Preview changes → Generate
Fine-tune your voice generation with advanced parameters that control speed, pitch, emotion, emphasis, and pronunciation. These controls give you precise control over the delivery and feel of your voice overs.