Cartesia · Rate Limits

Cartesia Ai Rate Limits

Cartesia enforces concurrency-based limits rather than classic requests-per-minute quotas. Each plan caps the number of simultaneous TTS requests, simultaneous STT requests, and active agent slots; a single TTS WebSocket connection can multiplex "dozens" of concurrent generation contexts within its plan's TTS concurrency ceiling. Usage above the plan's monthly credit allowance is billed or blocked depending on account configuration.

Cartesia Ai Rate Limits is the machine-readable rate-limit profile for Cartesia on the APIs.io network, in the API Commons Rate Limits shape.

It captures 15 rate-limit definitions, measuring connections, agents, contexts, frames, and seconds.

An exhausted limit returns HTTP 429.

This profile was written by API Evangelist and has not been verified against a page the provider published; treat every limit as unconfirmed until a dated transcription replaces it.

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

Tagged areas include AI, Voice AI, Text to Speech, Speech to Text, and WebSocket.

15 Limits Exhausted: HTTP 429
Method: generated, dated 2026-07-02.
Written by API Evangelist on 2026-07-02 and not verified against a page the provider published. Treat every limit as unconfirmed until a dated transcription replaces it.
View Source
AIVoice AIText to SpeechSpeech to TextWebSocketRate LimitingQuotasConcurrency

Limits

Concurrent TTS Requests (Free) account
connections
2
Applies to /tts/bytes, /tts/sse, and /tts/websocket combined.
Concurrent TTS Requests (Pro) account
connections
3
Applies to /tts/bytes, /tts/sse, and /tts/websocket combined.
Concurrent TTS Requests (Startup) account
connections
5
Applies to /tts/bytes, /tts/sse, and /tts/websocket combined.
Concurrent TTS Requests (Scale) account
connections
15
Applies to /tts/bytes, /tts/sse, and /tts/websocket combined.
Concurrent STT Requests (Free) account
connections
8
Applies to /stt, /stt/websocket, and /stt/turns/websocket combined.
Concurrent STT Requests (Pro) account
connections
12
Applies to /stt, /stt/websocket, and /stt/turns/websocket combined.
Concurrent STT Requests (Startup) account
connections
20
Applies to /stt, /stt/websocket, and /stt/turns/websocket combined.
Concurrent STT Requests (Scale) account
connections
60
Applies to /stt, /stt/websocket, and /stt/turns/websocket combined.
Agent Slots (Free) account
agents
1
Number of configured voice agents allowed simultaneously.
Agent Slots (Pro) account
agents
3
Number of configured voice agents allowed simultaneously.
Agent Slots (Startup) account
agents
5
Number of configured voice agents allowed simultaneously.
Agent Slots (Scale) account
agents
10
Number of configured voice agents allowed simultaneously.
TTS WebSocket Context Multiplexing connection
contexts
dozens per connection (published guidance, not a hard number)
A single wss://api.cartesia.ai/tts/websocket connection can run many concurrent context_id generations; still bounded by the account's overall concurrent TTS request limit.
STT WebSocket Audio Cadence connection
frames
100ms recommended chunk size
Binary audio frames should be sent in roughly 100ms chunks matching the negotiated encoding and sample_rate.
Access Token Lifetime token
seconds
3600
Short-lived scoped tokens minted via POST /access-token expire after at most 3600 seconds.

Policies

Concurrency Over Rate
Cartesia governs load primarily through simultaneous connection/request ceilings per plan rather than a rolling per-minute request counter.
Enterprise Custom Concurrency
Enterprise agreements can raise TTS/STT concurrency and agent slot limits beyond the Scale tier.
Backoff Strategy
Clients should implement exponential backoff with jitter and honor Retry-After on 429 responses, and should reuse a single WebSocket connection across many contexts rather than opening one per generation.

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/cartesia-ai-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 form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

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