Back to all models

ByteDance

Audio

Seed Audio 1.0 Text-to-Speech

Synthesizes speech or audio from text with optional audio or image 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 calm, warm older man's voice, unhurried, with the sound of wind and distant waves behind him and the slow creak of a wooden door. He reads a lighthouse keeper's log entry in a quiet, steady tone: "Third of November. Wind from the north-west, freshening after midnight. The lamp burned clean until dawn. Two fishing boats passed the point at first light, both riding low and heavy. The gulls have come back to the rocks, so the storm is over. Kettle on. All is well." The wind fades gently as he finishes.

More models

Browse allBrowse all models