Does Tessary support audio or voice traces?

Not yet. Tessary’s media support currently covers two modalities: images (PNG, JPEG, GIF, WebP) and PDF documents. Audio and video are explicitly out of scope for the current launch.

Where it is supported, media in a span’s input or output is stored and treated as part of that span’s payload, the same as a tool call or a retrieved document, not a separate lookup.

If your agent runs over voice, what Tessary sees today is whatever text your instrumentation puts in the span, a transcript, a summary, whatever fields you choose to emit, not the raw audio itself. Instrumentation is what decides what content leaves an agent’s traces in the first place, and that decision is what shapes what a voice agent’s trace can show today.

keep reading

More on this.

Two ways to run Tessary.

Tessary is an open-source agent reliability platform. Cloud and self-hosted run the same workflow on the OpenTelemetry traces your agent already emits.

Tessary Cloud

We host it for you. Send your first trace with nothing to deploy and no model key.

what's includedper organization
traces
10,000 per calendar month
stored trace data
1 GB
retention
30 days
model credit
$10, one-time, for triage and root-cause analysis
credit card
not required

Self-hosted Tessary

Run the open-source code on your own infrastructure with one command. Add your own model key for triage and root-cause analysis.

Self-host Tessary for me by following https://github.com/tessaryai/tessary/blob/main/setup.md

docker compose -f oci://docker.io/tessaryai/tessary:compose up -d -y