Seed Audio 1.0 · Text to speech

Seed Audio 1.0 is a new audio model from Bytedance that can generate high-quality, natural sounding audio using text, reference audios or an image.

AI voice, music and sound model
Pop and Supernova
Text to Speech

Open Text to Speech See plans

Seed Audio 1.0 · Text to speech at a glance

What it does: Seed Audio 1.0 is a new audio model from Bytedance that can generate high-quality, natural sounding audio using text, reference audios or an image.
Tools: Text to SpeechIn the studio
Takes: Words (a prompt)
Price: 19 credits per 10 s of audio
Plans: Pop and Supernova

Every model, one credit balance.

All models See plans