









Seed Audio 1.0 is ByteDance Seed's multimodal AI audio generation model for creating complete sound scenes from text, images, or audio references. It can generate multi-speaker dialogue, emotional delivery, native accents, ambience, background music, and foley-style sound effects in a single prompt. The platform is designed for longer audio scenes and supports layer-aware output for creative projects such as films, advertisements, podcasts, games, education, and XR prototypes.
Write a sound-scene prompt describing the characters, language, emotion, location, dialogue, ambience, music, sound effects, and timing. Optionally add up to three audio references or one image reference, choose voice and output settings, set a credit limit, and generate the audio. Review the result, then download, copy, or revise it.
More Contact, visit the contact us page()
Seed Audio 1.0 Company name: .
Seed Audio 1.0 Company address: .
More about Seed Audio 1.0, Please visit the about us page().

Free
$0
10 free signup credits, up to approximately 8 seconds per generation, maximum 2-minute audio generation, API access, and priority support
Pro
$19.99 per month
30,000 credits per year, up to approximately 400 total audio minutes, reference voice uploads, priority support, maximum 2-minute generations, and API access. Annual billing is displayed at approximately $16.66 per month.
Max
$49.99 per month
90,000 credits per year, up to approximately 1,200 total audio minutes, all Pro features, a larger production buffer, team-friendly usage, maximum 2-minute generations, and API access. Annual billing is displayed at approximately $41.66 per month.

Social Listening