Skip to main content

Audio. Redesigned, with a new model

By Steven Van ·

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 announced 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.

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

Read the original announcement →

Read Audio. Redesigned, with a new model on Creators Toolbox