Back to all models

ByteDance

Audio

Seed Audio 1.0 Multilingual Text-to-Speech

Synthesizes multilingual speech and audio with timing control and optional references.

Cost depends on your settings.

Read docs
Input

Enter speech text or instructions; refer to audio samples as @Audio1, @Audio2, or @Audio3.

Output
Example
00:00

Try an example

  • A clear, friendly female announcer's voice with the light echo of a ferry terminal hall, gulls and a distant engine hum in the background. She speaks calmly, first in English, then repeats the same announcement in Spanish: "Good evening. The last ferry to the north island leaves from pier four in ten minutes. Please have your tickets ready and mind the gap as you board." "Buenas noches. El último ferry a la isla norte sale del muelle cuatro en diez minutos. Tengan sus billetes preparados y cuidado con el hueco al subir." A soft two-note chime ends the announcement.

More from ByteDance

Browse allBrowse all models