A voice model developed by Alibaba for advanced text-to-speech synthesis.
Parameters
Undisclosed
Context Window
License
Proprietary
Release Date
2026-07-14
API Pricing
Input Price (per 1M tokens)
$0.2
Output Price (per 1M tokens)
$
Billing Mode: standard
Strengths
- •High-fidelity, natural, and expressive speech output.
- •Supports a wide range of voices and stylistic controls.
- •Superior handling of context, emotion, and rhythm in speech.
Weaknesses
- •Higher computational cost compared to lighter models.
- •Processing time may be longer for ultra-high quality synthesis.
- •May require more detailed input for optimal stylistic output.
Use Cases
- •Professional-grade audiobook and podcast narration.
- •High-quality voiceovers for commercials and videos.
- •Creating expressive and character-driven dialogue for games or media.