Release|Mar 20, 2024|6 min read
Introducing next-generation audio models in the API
New voice generation capabilities with improved quality and control.
We're pleased to announce our latest audio generation models, bringing unprecedented quality and control to speech synthesis and audio processing.
Key Features
Our new audio models deliver more natural-sounding voices with improved prosody, emotional range, and pronunciation accuracy. The system now handles multiple languages more effectively and can maintain consistent voice characteristics across long-form content.
The API now supports adjustable parameters for speech rate, pitch variation, and stylistic elements, giving developers precise control over the audio output.