Narakeet · Rate Limits

Narakeet Rate Limits

Narakeet enforces a default request quota of 86,400 requests per day (an average of 1 request per second) per account. Higher limits are available on request by contacting Narakeet. Beyond the request-count quota, throughput is bounded by content-size limits per call and by processing-time ceilings: the short-content streaming audio mode accepts about 1 KB of input and must complete within roughly 30 seconds, while the long-content polling audio mode accepts about 1024 KB and may take up to about 45 minutes to build. The voice-listing and account-credits endpoints do not consume production credits but each call still counts toward the daily request quota, so caching their results (for example once per day) is recommended.

Narakeet Rate Limits is the machine-readable rate-limit profile for Narakeet on the APIs.io network, conforming to the API Commons Rate Limits specification.

It captures 7 rate-limit definitions, measuring requests, bytes, and seconds.

The profile also includes 3 backoff/retry policies defined and response codes documented for throttled.

Tagged areas include Text to Speech, TTS, Audio, Video, and Rate Limiting.

7 Limits Throttle: 429
Text to SpeechTTSAudioVideoRate LimitingQuotas

Limits

Daily Request Quota account
requests
86400 per day
Default quota, averaging 1 request per second. Higher limits available on request.
Request Rate account
requests
~1 per second
Implied by the 86,400/day default; sustained bursts above this are throttled.
Streaming Audio Input Size request
bytes
~1024 bytes (1 KB)
Short-content streaming mode (Accept application/octet-stream) only; larger input must use the polling mode.
Polling Audio Input Size request
bytes
~1048576 bytes (1024 KB)
Long-content JSON polling mode maximum input size.
Streaming Audio Processing Time request
seconds
~30
Short-content streaming builds must complete within about 30 seconds.
Polling Build Processing Time request
seconds
~2700 (45 minutes)
Long-content audio and video builds may take up to about 45 minutes.
Voice / Credits Endpoint Calls account
requests
counts toward daily quota
/voices and /account/credits consume no production credit but count against the 86,400/day request quota; cache results.

Policies

Retry and Backoff
On 429 responses, clients should back off with exponential delay and jitter and stay under the ~1 request/second average.
Poll Interval
When polling a build statusUrl, poll at a modest interval (for example every few seconds) rather than tightly looping, to avoid consuming request quota unnecessarily.
Cache Voice List
Cache the /voices response (recommended once per day) since the voice catalog changes infrequently and each call counts toward the quota.

Sources

Work with this as data

Every rate limit here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for rate limits

4 MCP tools reach this
  • find_rate_limitsBrowse and filter every rate limit in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools

Call it yourself

curl for this page
This rate limit 
curl "https://apis.io/api/v1/rate-limits/narakeet-rate-limits"
All rate limits 
curl "https://apis.io/api/v1/rate-limits?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.