Unified music generation framework
SeedMusic 1.0 combines auto-regressive language modeling and diffusion in one framework that adapts to evolving musician workflows.
Powered by ByteDance SeedMusic 1.0. Turn lyrics into full songs, convert scores to music, edit lyrics and melodies in generated audio, and clone singing voices with just 10 seconds of audio — all at 44.1kHz stereo quality.
Start Free NowSeedMusic 1.0 combines auto-regressive language modeling and diffusion in one framework that adapts to evolving musician workflows.
Generate 1-minute clips, 3-minute full songs, song imitations, or instrumental tracks from lyrics with fine-grained style control.
Convert musical scores into full vocal and instrumental tracks with interpretable lead sheet tokenization for precise control.
Edit lyrics and vocal melodies directly in generated audio. Symbolic representations let creators read and modify musical content.
Clone singing voices with just 10 seconds of audio. SeedMusic 1.0 delivers 44.1kHz stereo output with industry-leading quality.
Seed Music
Powered by SeedMusic 1.0
Access SeedMusic 1.0 inside your creative workflow to generate professional music with ByteDance's unified generation technology.
Start CreatingSeed Music is built for musicians, songwriters, producers, and content creators who need controllable, high-quality music from SeedMusic 1.0.
Try Seed Music
Convert scores to songs, iterate on lyrics and melodies, and explore new musical directions with SeedMusic 1.0.

Leverage vocal music generation, singing voice synthesis, and post-production editing in one unified workflow.

Generate custom background music and vocal tracks with style control for social and brand content.
Experiment with SeedMusic 1.0 and combine lyrics with style descriptions or score references to create studio-ready music tracks.
Start Creating
Discover Seed Music's advanced features powered by ByteDance SeedMusic 1.0's unified generation framework.
Start CreatingBuilt on audio tokens, symbolic tokens, and vocoder latents — each chosen to best support musical workflows from ideation to delivery.
Covering clip generation, full songs, song imitation, instrumentals, score conversion, editing, and voice cloning in one platform.
Edit lyrics and vocal melodies directly in generated audio using symbolic representations creators can read and modify.
Imitate any voice from 10 seconds of singing or speech — no large-scale training required, with 44.1kHz stereo output.
ByteDance's Music Information Retrieval models power beat tracking, key and chord detection, and symbolic feature extraction.
From ByteDance's SeedMusic 1.0 launch to score-to-song workflows, Seed Music empowers musicians, songwriters, and content creators across ten creative tasks.
Convert scores to full songs, edit lyrics and melodies, and iterate on musical ideas with SeedMusic 1.0 controllable generation.
Generate custom background music and vocal tracks for social content with style-controlled Seed Music output.
Leverage SeedMusic 1.0's unified framework for vocal music, instrumental tracks, and post-production editing.
Create on-brand music with audio references and style descriptions for campaigns and product launches.
Join creators using ByteDance SeedMusic 1.0 to produce high-quality tracks. Seed Music makes professional music generation accessible to everyone.
Powered by ByteDance SeedMusic 1.0