Runtime & operations

Operate speech assessment with confidence.

Manage environments, protect usage, monitor performance, and meet privacy requirements with production controls built around the same assessment API.

  • Scoped API keys
  • Hard usage caps
  • Zero audio retention
Production overviewOperational
Chivox speech assessment API usage and latency analytics dashboard
99.95%
enterprise SLA
240 ms
p50 latency
0 sec
audio retention
01 / Control

Control access and usage before traffic scales.

Separate environments, enforce limits, and route alerts without rebuilding the integration or adding a second operations stack.

API keys dashboard floating over a desk — Dev, Staging, and Prod keys with usage bars
01 / Environment access

Separate environments without changing your integration

Use scoped keys for development, staging, and production. Rotate access safely while every environment keeps the same endpoint and response contract.

Scoped keysSafe rotation
Spend limits panel with evaluation-point gauge and monthly or daily caps
02 / Usage protection

Set enforceable limits before traffic scales

Assign a monthly cap to each key. When a limit is reached, the API returns a structured 429 so your product can degrade gracefully.

Per-key capStructured 429
Notification settings with alert thresholds and a low-balance toast
03 / Proactive alerts

Catch usage risk before users feel it

Notify engineering and operations by email or webhook as usage approaches a limit, leaving time to investigate, increase capacity, or adjust traffic.

Email alertsWebhook thresholds
02 / Observe

See issues before they reach users.

Track usage by key, inspect latency and error reasons, and understand which tools are driving traffic from the dashboard or export API.

  • Per-key usage
  • Latency percentiles
  • Tool breakdown
  • Structured error reasons
Explore monitoring in the docs
Per-key speech assessment API usage charts
03 / Trust

Built for sensitive audio and production traffic.

Keep audio ephemeral while relying on a runtime already operating at billions of evaluations per year.

Stateless speech assessment streaming and zero audio retention
Zero-retention streamingTTL 0s

Audio in. Assessment JSON out.

Audio is scored in memory, never used for training, and not stockpiled by the scoring runtime.

Global speech assessment API status and latency
Production scale9.2B+ / year

A runtime built for peak traffic.

9.2B+ evaluations per year, p50 latency of 240 ms, and a 99.95% uptime SLA on the enterprise tier.

Runtime & operations FAQ

Questions teams ask before launch.

Can I set usage limits for each speech assessment API key?

Yes. Each key can have its own monthly limit and environment scope. When the hard cap is reached, calls return a structured 429 response instead of failing ambiguously.

Does Chivox retain audio used for speech assessment?

Streaming audio is scored in memory and is not retained for model training. Your application receives structured assessment JSON without creating an additional stored audio copy in the scoring runtime.

What production monitoring is available?

The dashboard shows per-key usage, latency percentiles, tool breakdowns, and error reasons. Teams can also export usage data through the API and route threshold alerts through email or webhooks.

Ready to put speech assessment into production?

Start with free credits, or talk with the team about volume, security, and enterprise SLA requirements.

Start building