seed-audio mark

Seed Audio 1.0 Text to Speech

Seed Audio 1.0 converts text to speech (TTS) with 20 preset multilingual voices (English, Chinese, Japanese, Spanish, and more) and voice cloning from up to 3 reference audio clips. Use for voiceover, narration, dialogue, multilingual speech, character voices, and one-off voice cloning from an audio sample.

Inputs

Text

Outputs

Audio

Lab

ByteDance

Launch your first agent today

Build without code. Share without limits.