Skip to content

Changelog: Seed Audio 1.0. Score a whole scene in one pass

2026-06-27 · changelog: model release · Higgsfield · original

Topic: Audio, voice & music · mode: Release note · tags: vendor claims

Higgsfield's changelog of 27 June 2026 announces ByteDance's Seed Audio 1.0 in the Audio tab: speech, sound effects and music generated together from one prompt, multi-speaker voices, text, image or audio references, voice cloning from up to 3 references.

What is said

  • Seed Audio 1.0: speech, effects and music in one pass, how to start, availability

What is said

★ — how much it matters to the source.

  • ★★★ Higgsfield's changelog of 27 June 2026 announces ByteDance's Seed Audio 1.0, which generates speech, sound effects and music together from one prompt instead of three tools and a manual mix. · ByteDance
  • ★★ Higgsfield says Seed Audio 1.0 is multi-speaker: several voices hold across a scene, with control of emotion and accent.
  • ★★ Seed Audio 1.0 generates ambience, music and Foley: rain, traffic, room tone, a musical bed, footsteps and textures.
  • ★★ Seed Audio 1.0 can be guided by a text, an image or an audio reference.
  • ★★ To use Seed Audio 1.0 on Higgsfield: Audio → model selector → Seed Audio, then describe the scene, including how long each element should run. · Higgsfield Audio
  • ★★ Seed Audio 1.0 outputs WAV, MP3, PCM or OGG.
  • ★★ Voice cloning in Seed Audio 1.0 takes up to 3 audio references. · voice cloning
  • ★★ Seed Audio 1.0 has no duration field: the length of the audio is set through the prompt.

Threads in this video

  • launched · Seed Audio on Higgsfield — Higgsfield's changelog of 27 June 2026 announces ByteDance's Seed Audio 1.0, which generates speech, sound effects and music together from one prompt instead of three tools and a manual mix.
  • milestone · Higgsfield Audio — To use Seed Audio 1.0 on Higgsfield: Audio → model selector → Seed Audio, then describe the scene, including how long each element should run.

Where the stories that moved here went next

Mentioned

Central: Seed Audio 1.0

Also: ByteDance · Higgsfield Audio · Seed Audio · voice cloning

Also centred on Seed Audio 1.0: How to Make a Short Film With AI: The Full Pipeline From Script to Final Cut · How to Keep the Same AI Voice Across Every Video: Consistent AI Audio Explained

← Previous: How to Turn Your Own Footage Into Cinematic VFX with Seedance 4K: Guide with Ready-To-Use Prompts · Next → Changelog: App Builder. Describe a site, get a live URL