Text to speech failed request: charged? Sume dry_run and cap
A TTS job that fails on Sume's duration limit captures no credit. Use dry_run to preview cost and max_spend_usd to cap it before a paid request.
On Sume, a text-to-speech job whose audio runs past 1200 seconds fails with tts_duration_exceeded and no credit is captured. More generally, Sume reserves the estimate on submit, captures it on success, and releases or refunds it for failed jobs. Preview a request with dry_run and bound it with max_spend_usd.
Sume facts are from the OpenAPI TTS schema, the MCP tts_create description and the docs on generation admission, read 2026-09-30.
What does Cartesia say about failed requests?
Its pricing page says credits are only used by successful requests and errors will not consume credits, with standard TTS at approximately 1 credit per character. That is Cartesia's own billing, not a statement about Sume.
What does a failed Sume TTS job cost?
| Situation | What the docs say |
|---|---|
| Audio over 1200 s | Fails with tts_duration_exceeded (no credit capture) |
| Failed job or failed queue admission | Reservation is released or refunded where applicable |
| Success | Reserved usage is captured |
| Rate | Paid per transcript character: $0.0475 per 1,000 characters |
How do dry_run and max_spend_usd work?
The MCP tts_create tool takes {idempotency_key, payload, dry_run?, max_spend_usd?}. The description says dry_run previews cost and max_spend_usd caps it. The idempotency_key is required, and the transcript is 1 to 20000 characters.
Run dry_run first on a long script, then send the paid call with a max_spend_usd just above the preview.
How do I avoid paying twice for a retry?
Reuse the same idempotency key when a submit is retried, and do not submit a new paid job for the same intent just because a wait ran out. Long scripts should be split below the 1200-second ceiling; see TTS 1200-second limit.
Sources
Related posts
More in Pricing
- Where did the Sume Credits page go? Billing & subscription
The dashboard surface once called Credits is now Billing & subscription: plan status, balance and manual top-ups. What the API can read and what it cannot.
- Whisper API cost per minute, and what an hour costs
OpenAI lists Whisper at $0.006 per minute and gpt-4o-mini-transcribe at $0.003. Here is the per-hour math next to Sume STT 1.0's per-minute rate.
- How Sume pricing works: plans, one wallet, published model rates
Sume plans set access and concurrency. Usage draws from one prepaid wallet at each model's published USD rate, for generation, the Agent, Formats, and the API.
- AI avatar video API pricing: cost per second and per minute
Sume bills AI avatar video per second by quality tier, with separate rates when you send a product image. Per-minute costs for standard, plus, and max.
Written by Sume