Diffio API models

Model cards for audio restoration

Compare speed, fidelity, and pricing, then pick the model id that fits your workflow. You can cross-check rates on the API pricing page or start implementation with the developer quickstart.

View pricing

Model cards

Each card includes the model id, best use cases, and the current API rate. For the full API flow, review the API overview.

Diffio 2.0

Fast, reliable cleanup for everyday restoration.

Balanced
Model iddiffio-2
Best forGeneral restoration, quick turnaround, high volume work.
Language supportMultilingual
  • Fastest turnaround in the product lineup.
  • Reliable cleanup for interviews and podcasts.
  • Best fit for high volume production queues.
Price per secondLoading pricing
Estimated per hourLoading pricing

Billed by processed seconds, invoiced monthly. Minimum billable duration is 60 seconds per generation request.

View billing details

Diffio 3.5

Best quality reconstruction for demanding speech.

Best
Model iddiffio-3.5
Best forCritical clarity work and detailed transcripts.
Language supportEnglish only
  • Improved clarity in noisy rooms.
  • Sharper consonants and tighter detail.
  • Stronger alignment for transcript review.
Price per secondLoading pricing
Estimated per hourLoading pricing

Billed by processed seconds, invoiced monthly. Minimum billable duration is 60 seconds per generation request.

View billing details

Get started

Ship your first restoration quickly

Generate an API key, follow the docs, and run a request in minutes. If pricing is the blocker, go back to API pricing.

View documentation