Inputs:
- Text prompt
- Voice
- Emotion (optional)
- Speed (optional)
- Volume (optional)
- Pitch (optional)
- Output format (optional)
Limits:
- Audio output only
- Supports 32+ languages
- HD is higher quality but slower and more expensive than Turbo
- Streaming is supported
- Voice cloning depends on the selected endpoint/settings
Tips:
- Use HD for final voiceovers, narration, dialogue, trailers, and polished speech
- Use Turbo for faster drafts and cheaper iteration
- Keep sentences clean and well-punctuated for better pacing
- Use emotion control when the delivery needs a specific tone
- Use pitch, speed, and volume carefully; extreme values can sound artificial