Pricing

Breeze uses credits shared across the platform. Each request consumes billable units based on text length and model.

How we meter

  • Text-to-speech: per character after Unicode normalization.
  • Voice design: per generated preview. When preview_count is omitted, Breeze generates one preview.
  • Voice cloning: flat per-job cost.
  • List, get, and delete (catalog reads): not billed.

Generation concurrency

Each plan includes a maximum number of simultaneous generations: synthesis jobs admitted or running at the same time. Paid plans also include a small queued generation buffer. Studio and Developer API jobs share the same per-user pool. Sync text-to-speech, streaming text-to-speech, async text-to-speech, voice design, and voice cloning all count toward these limits. Voice design counts each requested preview as one generation. When preview_count is omitted, Breeze generates one preview.

PlanConcurrent generationsQueued generations
Free30
Starter62
Creator103
Pro205

Where to see your spend

Balance, last 30 days of usage, and per-request charges are on the usage page.

Free credits and top-ups

Credits are shared across Studio and the developer API. Top up on pricing.