How we meter
- Text to speech: per character after Unicode normalization.
- Voice design: per generated preview. When
preview_countis 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. A generation is admitted or running synthesis work. 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.| Plan | Concurrent generations | Queued generations |
|---|---|---|
| Free | 3 | 0 |
| Starter | 6 | 2 |
| Creator | 10 | 3 |
| Pro | 20 | 5 |
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.Plan your usage
Rate limits
Understand concurrent generation limits, queue behavior, and retry guidance.
Usage page
Review balance, recent usage, request charges, and credit consumption.
Text to speech guide
Choose sync, streaming, or async delivery with cost and concurrency in mind.
Errors
Handle insufficient credits, concurrency limits, capacity, and retryable failures.