Skip to main content
BreezeBlue uses credits shared across Studio and the Developer API. Text to speech and voice previews are metered by weighted text length: 10 billable units = 1 credit.

How we meter

  • Text to speech: per character of the request text. Chinese, Japanese and Korean characters (Han ideographs, kana and Hangul) count as two billable units each; every other character (Latin letters, digits, spaces, punctuation including CJK punctuation, emoji) counts as one. 10 billable units = 1 credit.
  • Realtime text to speech: the same per-character rule applied to each appended turn’s text, committed when the turn settles; turns that never produce audio are not billed. See the realtime guide.
  • Voice design and remix: bill the preview script once per generation request, including a design request with preview_count=3. At least one successful preview captures that single script charge; if all previews fail, the full reservation is released. Omitting preview_count generates one design preview.
  • Voice cloning: bill the generated preview script once, using the same character and CJK weighting. Web reference-audio upload analysis costs an additional 1 credit per analysis. Saving an existing generated preview does not incur another generation charge.
  • Voice localization: bill the final target-language preview script once. Failed jobs release their reservation, and saving the preview does not incur another generation charge.
  • List, get, and delete catalog reads: not billed.
For voice previews, text_characters records the raw script length and billable_units records its weighted character count. Candidate count does not multiply the charge. Retries with the same idempotency key reuse the original generation and reservation. Text-to-speech example: 你好世界hello is 9 characters, 4 of them CJK, so it bills 4 × 2 + 5 × 1 = 13 billable units = 1.3 credits. In usage records, text_characters is the raw character count (9) and billable_units is the charged unit count (13).

Generation concurrency

Each plan includes a maximum number of simultaneous generations. A generation is admitted or running synthesis work. Studio and Developer API jobs share the same per-user pool. Requests over the limit fail fast with 429 GENERATION_CONCURRENCY_EXCEEDED and Retry-After. Sync text to speech, streaming text to speech, async text to speech, voice design, voice cloning, and voice localization all count toward these limits. A voice preview batch uses at most the account limit at once; additional candidates wait within the batch without reducing the requested preview count. Separate requests still share the same account pool. Free uses the standard queue. Paid plans provide the concurrency tiers shown on Pricing: GET /v1/entitlements returns the effective account limit, including approved custom limits and temporary paid-cycle allowances.

Where to see your spend

Balance, last 30 days of usage, and per-request charges are on the usage page. For teams or shared accounts, assign a credit limit to each API key on the API keys page. Key budgets control how much of the shared account balance an employee, application, or environment can consume. Batched TTS settlement permits up to 300 seconds between balance and budget checks, so usage can exceed the configured amount. They do not preallocate credits, and resetting a key budget does not refund the account balance. See Authentication for the exact semantics.

Settlement visibility

For accounts configured for batched TTS settlement, audio generation finishes before credits are posted. Settlement runs every 60 seconds. The balance response includes settlement_pending and settlement_interval_seconds; pending charges are not yet reflected in the numeric balance. An exhausted admission snapshot refreshes after 5 seconds, which also allows top-ups to restore access. Credentials, account restrictions, text limits and shared concurrency limits remain enforced.

Free credits and top-ups

Credits are shared across Studio and the Developer API. Top-ups provide 10,000 credits for $3, with a $5 minimum purchase and credits rounded up to an integer. For example, $5 provides 16,667 credits and $9 provides 30,000 credits. See pricing.

Plan your usage

Rate limits

Understand concurrent generation limits and retry guidance.

Usage page

Review balance, recent usage, request charges, and credit consumption.

Get usage metering

Query aggregated usage with daily buckets and recent requests programmatically.

Get account balance

Check the current credit balance and recent top-ups before large batch runs.

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.