Seed Audio 1.0
Generate dialogue, music, and scene sound effects from text, images, or audio
About Seed Audio 1.0
Seed Audio 1.0 is ByteDance Seed's all-in-one audio generation model, capable of creating multi-speaker dialogue, emotional expression, native accents, ambience, background music, and foley effects around complete sound scenes. Enter a sound-scene prompt online, optionally add an audio or image reference, choose output settings, then generate and audition the result in the workspace. It is suited to precisely timed foley, original music, multilingual dialogue, and reusable voices that you own or are authorized to use.
Best for
Best use cases
Create multi-speaker dialogue
Generate original music
Create precisely timed foley
Generate ambience and scene sound effects
Features
Scene audio generation
Generate complete audio scenes from sound-scene prompts.
Reference inputs
Use up to three audio references or one image reference to guide sound style, mood, and setting.
Multivoice expression
Generate multi-speaker dialogue, emotional expression, and native accents.
Music and foley
Create original music, ambience, and precisely timed foley effects.
Pros
- Supports text, image, and audio references
- Covers dialogue, music, ambience, and foley
- Supports multiple speakers, emotional expression, and multilingual dialogue
Cons
- Voice cloning is limited to voices you own or are explicitly authorized to use
- The free quota generates about 8 seconds each time; each audio file can be up to 2 minutes