Meet Seed Audio 1.0 — Now open for enterprise access application.
A pioneering non-streaming TTS model that generates voice, music, and sound effects in a single pass.
Key capabilities:
• Natural speech generation
• Preset voices
• Reference audio guidance
• Image-guided audio
• Fine-grained control over speed, volume, pitch, and output format
Want early access? Follow the steps below ↓
显示更多