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

# The tracing SDKs

> Standard OpenTelemetry, curated: one install, one line, no instrumentation code of our own — and an eject guarantee that means uninstalling loses nothing.

The Omnia tracing SDKs, [`@omnia-voice/tracing`](/sdks/typescript) for Node
and [`omnia-tracing`](/sdks/python) for Python, stream your LLM traffic to
Omnia, where you grade it, calibrate a judge against your own standards, and
find out **with confidence intervals** whether a cheaper model holds up on
your production traffic. Your inference does **not** move: requests keep
going to your current provider; only trace telemetry flows to Omnia.

## No instrumentation code of our own

Each package contains **no instrumentation code of its own**. It pins and
configures the ecosystem's standard OpenTelemetry instrumentations, which
gives it a property no other tracing SDK offers: **you can uninstall it
without losing your instrumentation.** The identical setup in vanilla OTel is
documented on each SDK page (the eject guarantee); your spans are
byte-for-byte the same either way, and nothing proprietary ever goes on the
wire.

## When to use the SDK, and when not to

The SDK is one of four [integration paths](/capture/overview):

* **Already routing through the gateway** or
  [bringing your own key](/reference/bring-your-own-key)? You don't
  need an SDK; the gateway captures your traffic in the request path.
* **Already emitting OpenTelemetry** (Vercel AI SDK telemetry, Pydantic AI,
  an existing OTel setup)? You don't need this package at all; three env
  vars point your existing exporter at Omnia. See
  [OTLP trace ingest](/reference/otlp-ingest).
* **No OTel yet, and your inference must not move?** Use the SDK: one
  install, one line, standard OpenTelemetry underneath.

## Privacy

Span **structure** is always stored. Model-call **content**
(prompts/completions) is stored only if your Omnia workspace has
[request logging](/reference/request-logging) enabled, under your retention
window, with the same scrubbing and size caps as gateway traffic.

## Packages

| Language          | Package                                    | Install                            |
| ----------------- | ------------------------------------------ | ---------------------------------- |
| TypeScript / Node | [`@omnia-voice/tracing`](/sdks/typescript) | `npm install @omnia-voice/tracing` |
| Python            | [`omnia-tracing`](/sdks/python)            | `pip install omnia-tracing`        |

Both are Apache-2.0.