Resemble AI · Rate Limits
Resemble Ai Rate Limits
Resemble caps API throughput primarily through plan-based concurrency. Enterprise plans unlock higher concurrency limits, SLAs, and SOC 2 compliance. Specific HTTP RPS limits are not publicly documented.
2 Limits
Throttle: 429
AIVoiceTTSVoice CloningAudioRate LimitingQuotasThrottling
Limits
Concurrent Connections (Flex) account
see Flex plan
Flex tier concurrency cap; enterprise customers receive higher limits.
HTTP Requests account
not publicly documented
Policies
Backoff Strategy
Clients should implement exponential backoff with jitter and honor any Retry-After header.
Streaming Choice
Use HTTP streaming or WebSocket streaming for low-latency TTS to reduce per-request overhead.