Talo Request a pilot

Labelled robot video, back before your next training run.

Send your recordings. Talo returns boxes, tracksA box drawn around one hand or object in every frame, kept under the same name from start to end., action segmentsA stretch of time with one action name, such as grasp or pour, and exact start and end times. and task descriptions in the schemaThe file layout and field names your training code already expects. your pipeline already reads.

Request a pilot See a labelled sample
Before
Before. A raw frame, as you would send it.
After right hand bottle cup action: pour
After. Object tracks and an action label, from the sample below. right handbottlecup

Problem

Robot experiments stall while recordings wait for labels.

10 hours of footage is 1,080,000 frames to label.

Labels come back with no rules and no check record.

Every export needs converting.

How it works

Labelling moves off your team's desk.

Today

  1. Record
  2. Wait for labelsStall
  3. Convert formatStall
  4. Train

With Talo

  1. Record
  2. Talo labels, checks and formats

    Label. Boxes, tracks, action segments and task descriptions.

    Check. Checked against the rules you agreed, with a check log.

    Format. Delivered in the schema your pipeline already reads.

  3. Train
  1. 1

    Send a brief

    Robot, tasks, labels, a few clips.

  2. 2

    Agree the rules

    Action names, segment boundaries, what counts as failure.

  3. 3

    Check a pilot batch

    You review a small batch before any larger order.

  4. 4

    Receive each batch

    Your schema, with the rules and a check log.

One episode, as delivered

Pick up the bottle with the right hand and pour water into the cup.

  1. grasp0.0 to 2.5 s
  2. tilt2.5 to 4.5 s
  3. pour4.5 to 6.5 s
  4. return6.5 to 8.0 s
  • Tracks right hand, bottle, cup
  • Segments 4, no gaps or overlaps
  • Check 28 frames, 9 corrections logged
"segments": [
  { "start_s": 0.0, "end_s": 2.5,
    "action": "grasp",
    "description": "Right hand closes on the bottle." },
  ...
],
"review": {
  "frames_checked": 28,
  "threshold_px": 4,
  "corrections": [ ... ]
}
From the sample below. Field names follow your schema; this file uses Talo's default.

Who it's for

Teams that train manipulation policies on video.

Academic robotics labs

You sendTeleoperation or egocentric recordings
You getLabels, plus written rules your paper can cite

Humanoid and robotics startups

You sendRecordings and your training schema
You getLabels in your training format
See the case study Need recordings too? See collection

Sample

Check our work before you talk to us.

A demonstration clip labelled by Talo for this site; not customer work. Read the demo format and limitations.

First frame of the sample clip: a robot hand holding a bottle beside a cup.

Pour water, head camera

Task description

Labels by Talo, checked in a second pass by the same annotator and not independently reviewed.

Request a pilot

Case study

How a research lab got months of labelling done in weeks.

Case study · Annotation3 min A university research lab clears a 3,400-episode backlog and moves its old labels to a new 14-action list. 3,400 episodes · 5 weeks · 2.1% rework