BytePlus seed-tts text-to-speech. Paste text in any supported language and receive a natural-sounding audio file. Multiple voices (male, female, age range, tone) are available. Ideal for narration, e-learning content, podcast intros, accessibility audio, or turning long-form articles into listenable versions. Output content formats: Audio Pricing: Medium-low Audio output format: MP3. This module does not support continuous conversations. AI can make mistakes. Please verify important information.