# Seed Audio 1.0

- Date: 2026-06-30
- Type: model
- Credit: ByteDance / BytePlus
- Post: https://x.com/BytePlusGlobal/status/2071954152620732848
- URL: https://aifilmhistory.org/entry/seed-audio-1-0

Six days after Seedance 2.5, ByteDance opened enterprise applications for Seed Audio 1.0, a text-to-speech model that generates voice, music, and sound effects together in a single pass rather than routing each through a separate tool. It also does reference-audio cloning and image-guided audio that reads a still frame to produce matching ambience.

For AI filmmakers the pitch is a unified soundstage. Instead of stitching a TTS narrator, a music generator, and an effects library into one timeline, a single model voices the dialogue, underscores the scene, and lays in the room tone at once, the audio counterpart to what ByteDance is pushing on the video side. Enterprise beta through BytePlus, no public pricing.

Links:
- BytePlus — Seed Audio 1.0 announcement: https://x.com/BytePlusGlobal/status/2071954152620732848

---
Source: https://aifilmhistory.org/entry/seed-audio-1-0
Era: 2026 · The Shakeout
Last updated: 2026-10-14