Gen AI Speech + Podcast Editing

Gen AI Speech + Podcast Editing

Wondercraft helps content creators craft amazing audio experiences in any language, for ads, podcasts or audiobooks without the need of an expensive studio.

READ MORE

WATCH IT IN ACTION

Gen AI Speech + Podcast Editing

AudioShake powers Wondercraft tools for podcasters and content creators - YouTube

Working with AudioShake

Podcasters often struggle with overlapping dialogue in master recordings, limiting their ability to make precise edits. To address this, Wondercraft integrated AudioShake’s Multi-Speaker Separation technology, which isolates each speaker into individual tracks. This integration allows podcasters to upload audio from Notebook LM directly into Wondercraft, where AudioShake’s technology processes the file and separates the dialogue, even in complex, overlapping conversations.

This process enables podcasters to make targeted edits— adjusting volume levels per speaker, removing filler words, or cutting interruptions without affecting the rest of the conversation.

Wondercraft’s partnership with AudioShake showcases how advanced audio separation can transform content workflows, offering creators new levels of control and creative flexibility.

“AudioShake’s Multi-Speaker separation technology addresses a huge challenge in podcasting and audio production that’s long been impossible to tackle—separating voices in complex, overlapping conversations. By leveraging their API on our platform, Wondercraft users can isolate, edit, and enhance individual voices with ease, paving the way for the future of audio creation by unlocking new levels of clarity and precision in content production.”

Oscar Serrander
CEO, Wondercraft


Case Studies:

  1. ESPN opens up catalogs - A/V Editing
  2. Scaling CrunchLabs Videos Worldwide - A/V Editing
  3. Lyrics and Stems for Disney - Mixing
  4. Spatial Mixes of Bocelli Duets - Mixing
  5. Bringing Maria Callas’ Voice to Life - A/V Editing
  6. The Making of SZA's "Forgiveless" - Mixing

VIEW ALL