Hume AI · Rate Limits
Hume Ai Rate Limits
Hume rate-limits primarily through plan-based monthly TTS character allowances, EVI minutes, and concurrent connection caps. Specific HTTP RPS limits are not publicly documented; Expression Measurement is gated by job throughput.
Hume Ai Rate Limits is the machine-readable rate-limit profile for Hume AI on the APIs.io network, conforming to the API Commons Rate Limits specification.
It captures 5 rate-limit definitions, measuring characters, minutes, concurrent_connections, and requests.
The profile also includes 2 backoff/retry policies defined and response codes documented for throttled.
Tagged areas include AI, Voice, Empathic, Emotion, and Multimodal.
5 Limits
Throttle: 429
AIVoiceEmpathicEmotionMultimodalRate LimitingQuotasThrottling
Limits
TTS Characters/Month (Free) account
10000
~10 minutes of TTS audio.
EVI Minutes/Month (Free) account
5
Concurrent Connections (Free) account
1
EVI Minutes/Month (Business) account
12500
HTTP Requests account
not publicly documented
Verify with Hume support; standard 429 backoff applies.
Policies
Backoff Strategy
Clients should implement exponential backoff with jitter and honor any Retry-After header.
Plan Sizing
Choose plan tier based on monthly TTS character and EVI minute usage projections.
Sources
Work with this as data
Every rate limit here is available over the APIs.io API and to AI agents over MCP.