# Runware adds ByteDance's Seed Audio 1 model

By Steven Van · 2026-06-30

The model generates dialogue, sound effects, music and ambient sound from one prompt, plus voice cloning from up to three clips.

Runware has added **Seed Audio 1**, ByteDance's audio generation model, to its API. A single prompt can produce dialogue, sound effects, music, and ambient sound together.

- Multi-speaker conversations with distinct voices from one prompt

- Voice cloning from up to three reference clips

- Character voices derived from a portrait image

The model is available now through [Runware](<https://creatorstoolbox.com/tools/runware>), as [announced on X](<https://x.com/i/status/2071900903771177444>).

[View media](<https://video.twimg.com/ext_tw_video/2071900801438466048/pu/vid/avc1/1280x720/fJO6VdyilJ7nC1AY.mp4?tag=12>)

![Runware](<https://www.google.com/s2/favicons?domain=runware.ai&sz=128>)

Runware

Fast, low-cost AI inference API for image, video, and audio generation — run top models at scale without managing GPUs.

[View Runware →](<https://creatorstoolbox.com/tools/runware>)

[Read Runware adds ByteDance's Seed Audio 1 model on Creators Toolbox](<https://creatorstoolbox.com/blog/runware-seed-audio-1-from-bytedance>)

---
Canonical source: https://creatorstoolbox.com/blog/runware-seed-audio-1-from-bytedance