> ## Documentation Index
> Fetch the complete documentation index at: https://anam.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Session Performance

> Understand the performance indicators on the sessions page and fix slow response latency

The [sessions page](https://lab.anam.ai/sessions) in Anam Lab shows a
Performance card with four latency metrics for your recent sessions. Each
metric shows the median (p50), p95, and maximum across every conversational
turn in the selected time period, with a green, amber, or red indicator next
to it.

Latency data comes from session reports, which are produced for sessions
where Anam runs the conversational pipeline (turnkey, custom LLM, and
ElevenLabs agent sessions). You can fetch the same data programmatically with
the [aggregate analytics
endpoint](/api-reference/sessions/get-aggregated-session-analytics) or drill
into a single session with the [per-session analytics
endpoint](/api-reference/sessions/get-session-analytics).

## What the indicators mean

The indicator compares your median (p50) for the selected period against
thresholds derived from latency across all production sessions:

* **Green** — at or better than a healthy production median. No action
  needed.
* **Amber** — slower than typical. Users will notice the delay; review the
  suggestions below.
* **Red** — slower than roughly 90% of production sessions. Something in
  your configuration or environment is adding significant delay.

| Metric           | Measures                                          | Green  | Amber  | Red    |
| ---------------- | ------------------------------------------------- | ------ | ------ | ------ |
| Response latency | User stops speaking → persona starts speaking     | ≤ 1.5s | 1.5–3s | > 3s   |
| Transcription    | User stops speaking → transcript complete         | ≤ 0.5s | 0.5–1s | > 1s   |
| LLM first output | Transcript complete → first LLM output            | ≤ 1s   | 1–2.5s | > 2.5s |
| TTS first audio  | Speech generation start → persona starts speaking | ≤ 0.5s | 0.5–1s | > 1s   |

## Response latency

Response latency is the end-to-end delay your users experience: the time
from the moment they stop speaking to the moment the persona starts
speaking. It is the sum of the three stages below, so start by checking
which stage is amber or red and follow the guidance for that stage.

If all three stages are green but response latency is amber or red, the
gap is usually network transit between your users and Anam:

* Check where your users are located. Sessions are served from the closest
  Anam data center, so users far from one will see higher latency.
* Use the [per-session analytics
  endpoint](/api-reference/sessions/get-session-analytics) to find the slow
  sessions, then check their `clientMetadata` and location for a pattern.

## Transcription

Transcription latency is how long it takes to produce the final transcript
after the user stops speaking. Anam manages the transcription pipeline, so
this stage is normally well under half a second.

If it is amber or red:

* Review your [voice detection settings](/personas/session/voice-detection).
  A high `endOfSpeechSensitivity` can delay the point at which Anam decides
  the user has finished speaking.
* Check whether the affected sessions come from users on poor network
  connections; delayed or dropped audio extends transcription time.
* If it stays red across many sessions with default settings, contact your
  Anam representative or support — this stage is Anam-managed.

## LLM first output

LLM first output is the time from transcript completion to the first token
from the language model. This is usually the largest and most controllable
stage.

If it is amber or red:

* **Choose a faster model.** Larger models take longer to produce their
  first token. See [available LLMs](/personas/llms/available-llms) for the
  options and their trade-offs.
* **Shorten your system prompt.** Very long prompts increase time to first
  token. The [prompting guide](/personas/llms/prompting-guide) covers how to
  keep prompts effective and compact.
* **If you use a custom LLM**, host it close to Anam's infrastructure,
  make sure streaming is enabled, and measure your endpoint's own time to
  first token — Anam can only be as fast as your server. See
  [custom LLMs](/personas/llms/custom-llms).
* **Review knowledge and tools.** Knowledge retrieval and tool calls run
  during the response and add to the delay on turns that use them. Check
  the tool call timings on the
  [session endpoint](/api-reference/sessions/get-session) to see how long
  each call took.

## TTS first audio

TTS first audio is the time from the start of speech generation to the
persona actually speaking. This stage is tightly managed by Anam and sits
around half a second for almost all production sessions.

If it is amber or red:

* Try a different voice. Some voices and voice providers generate the
  first audio chunk faster than others; see
  [voice configuration](/personas/voices/configuration).
* If it stays red across voices, contact your Anam representative or
  support — this stage is Anam-managed.

## Digging deeper

* [Aggregate analytics
  endpoint](/api-reference/sessions/get-aggregated-session-analytics) —
  the same percentiles as the Performance card, filterable by persona, API
  key, client label, and session type, including the slowest individual
  turns in the period.
* [Per-session analytics
  endpoint](/api-reference/sessions/get-session-analytics) — per-turn
  timing for one session, so you can see exactly which stage was slow on
  which turn.