BytePlus opens enterprise access to Seed Audio 1.0
By Steven Van ·
The non-streaming model generates speech, music, and sound effects in one pass, with preset voices, reference-audio matching, and image-guided generation.
BytePlus has introduced Seed Audio 1.0, a non-streaming text-to-speech model that generates voice, music, and sound effects in a single pass rather than streaming audio incrementally.
- Natural-sounding speech synthesis
- A set of preset voices
- Reference-audio guidance, to match a supplied voice sample
- Image-guided generation
The model is now open for enterprise access applications.
BytePlus
ByteDance's AI-native cloud platform — tap the AI powering TikTok, including Seedance video and Seedream image models, LLMs, and enterprise APIs.
View BytePlus →