Or jump from this list on a smaller screen.

This is a page from the Audivra documentation. Developer exportsindex: http://127.0.0.1:3000/docs/llms.txt, full corpus: http://127.0.0.1:3000/docs/llms-full.txt, OpenAPI: http://127.0.0.1:3000/docs/openapi.json, Postman: http://127.0.0.1:3000/docs/postman.json. Press ⌘K to search docs.

Limits & quotas

Credits, plan caps, routing credits, rate limits, per-request text caps, and overage rules — one place for metered mobile and Global South integrations.

Credit metering

1 Audio character = 1 creditlen(text) on TTS and generate

1 Video second = 10 creditsBilled on completed render duration

1 STT second = 5 creditsCeil(duration) on POST /api/v1/stt and dub recognition

1 Music second = 8 creditsScore beds under talking-heads — same prepaid pool

1 Sound-effect clip = 20 creditsShort cues billed per clip

Monthly plan credits are a unified pool — TTS, video, STT, music beds, and SFX clips all draw from the same quota using the rates above.

Concept overview: Credits. Estimate a mix: usage calculator.

Routing credits

POST /api/v1/generate additionally deducts routing credits per execution node (separate from character/video metering). Default starting balance: 50 routing credits.

local_worker

1

routing credit / request

gpu_cluster

3

routing credits / request

external_api

3

routing credits / request

Node selection: Processing nodes

Per-request caps

LimitValue
Max text per cloud API request5,000 chars
Fast-path local routing (POST /api/v1/generate)< 500 chars
Local worker Kokoro cap500 chars

Rate limits

60 req/min
100 generate req/min paid
per API key

Per sk_live_ API key (hashed at enforcement) and per dashboard session. Enforced on Next.js /api/v1/* routes and the FastAPI gateway (:8080).

Response header: Retry-After: 60 on 429

Returns 429 Too many requests. Redis-backed when REDIS_URL is set; in-memory sliding window in local dev. Generate/avatar/dub/batch use a separate bucket: 100 req/min on paid plans, 60 on Free Trial. Override with RATE_LIMIT_PER_MINUTE env in private deployments.

PlanMediaUploadGenerate rpmBatchNeural lip-sync
free180s15 MB60Optional
starter600s80 MB10050Required
creator1800s250 MB100200Required
developer1800s500 MB100500Required

Batch enqueue is a queue, not parallel GPU occupancy. Paid jobs fail if neural lip-sync weights are unavailable.

Plan caps

PlanPriceCredits/mo~VideoHard capPAYGVoice slotsVideo
Free Trial$0/mo12,000~1200s video OR 12,000 char audioYes$0.040/1k after quota0480p · 128 kbps
Starter / Hobby$5/mo36,000~3600s video OR 36,000 char audioYes$0.040/1k after quota1720p · 192 kbps
Creator Pro$18/mo145,000~14500s video OR 145,000 char audioYes$0.035/1k after quota31080p · 256 kbps
Developer API$79/mo720,000~72000s video OR 720,000 char audioYes$0.032/1k after quota101080p · 320 kbps · Yes

Upgrade: Billing API

PAYG rules

  • All self-serve tiers — minimum $5 top-up · pause at $0 · no postpaid debt
  • 12,000 credits/mo — extend with PAYG wallet at $0.04/1k
  • 145,000 credits/mo — PAYG at $0.035/1k after quota
  • 720,000 credits/mo — volume PAYG at $0.032/1k

PAYG draws from prepaid creditBalanceCents when monthly quota is exceeded. At $0 balance, API returns 402. Top up via Pay As You Go.