At a glance
- Did you know
- Streaming speech recognition returns partial words while the user is still talking.
- Rule of thumb
- Send audio in small chunks to keep the transcript close to real time.
- Watch out
- Concurrency caps; latency on long utterances.
Its settings in ScaleMySystems
What you can change on it in the lab, and what each number does.
- Concurrency (slots)
- Calls it can work on at once (per instance when autoscaling). Needed slots ≈ calls per second × seconds each takes. Extra calls wait in the queue, then are rejected.
- Queue capacity
- Calls allowed to wait for a free slot. A bigger queue absorbs bursts but adds waiting time; 0 rejects straight away.
- vCPU
- CPU cores available. Needed ≈ calls per second × CPU per request ÷ 1000. Above about 90% busy it slows down and may crash.
- CPU per request (ms)
- CPU time each call burns. Part of what the component is; make the code cheaper to lower it.
- Latency (p50) (ms)
- Typical time one call takes here, before any calls it makes itself. Slots are held for this long.
- Latency (p99) (ms)
- The slowest 1% of calls. Callers must set their timeout above this or they cut off healthy calls.
- Timeout to dependencies (ms)
- How long it waits for each call it makes before giving up. Set it above the dependency’s p99 but low enough that a dead dependency does not hold every slot.
- Error rate
- Share of calls that fail on their own (bugs, declines, flaky tools). An agent that calls it on every step multiplies this.
- Quota (req/min)
- Calls allowed per minute (an API key or provider limit). Calls over it get 429s. Needed = calls per second × 60, with headroom.
Problems that start with it
- Voice assistant: transcription backs up A voice assistant transcribes speech, answers, and speaks the reply. Speech-to-text has 16 slots at 30 utterances a second.
- Voice replies lag A voice assistant’s text-to-speech has 20 slots and takes about 600 ms per reply at 50 replies a second.
- Medical scribe: redaction bottleneck A medical scribe transcribes visits, redacts PII and drafts notes. The redactor has 1 vCPU and 20 ms per note, at 100 notes a second.
- Voice agent: the model’s slow tail A voice agent transcribes speech (100–150 ms), asks a model (first token: 250 ms usually, 2.4 s for the slowest 1%) and speaks the answer. The call to the model waits up to 8 s and has nowhere else to go. Callers notice any silence over about a second.
Full lesson coming soon
Lessons are being added one component at a time: how it works, its settings, a live exercise to break and fix it, interview questions and a short check. See the Circuit breaker lesson for what one looks like.