# Audio. Redesigned, with a new model

By Steven Van · 2026-08-10

Audio has been redesigned. A new model, Qwen, has been added, along with advanced settings for audio models: control over emotion, format, pitch, and more.

[**Higgsfield**](<https://creatorstoolbox.com/tools/higgsfield>) announced [**Audio. Redesigned, with a new model**](<https://higgsfield.ai/creator-hub/changelog#audio-redesigned-with-a-new-model>) on August 10, 2026.

## What changed

Audio has been redesigned. A new model, Qwen, has been added, along with advanced settings for audio models: control over emotion, format, pitch, and more. Text to Speech. Generate speech from text using a preset voice, or upload or record your own. Voice Change. Swap the voice in an uploaded video while keeping the original delivery. Translate. Translate and lip-sync a video into another language, from a library of 18 languages. To get started: open Audio and pick Text to Speech, Voice Change, or Translate.

[![](<https://higgsfield.ai/thumbnail/default.jpg>)](<https://higgsfield.ai/creator-hub/changelog#audio-redesigned-with-a-new-model>)

![Higgsfield](<https://higgsfield.ai/icon.png>)

Higgsfield

AI video and image generation platform — create videos, edit with motion control, swap faces, and collaborate in real time.

[View Higgsfield →](<https://creatorstoolbox.com/tools/higgsfield>)

Sources

[Original source](<https://higgsfield.ai/creator-hub/changelog#audio-redesigned-with-a-new-model>)

[Read Audio. Redesigned, with a new model on Creators Toolbox](<https://creatorstoolbox.com/blog/higgsfield-audio-redesigned-with-a-new-model>)

---
Canonical source: https://creatorstoolbox.com/blog/higgsfield-audio-redesigned-with-a-new-model