A Slovak and English workflow
One programme.
Every layer.
A Slovak bulletin with an English interview can share one timeline: original speech, translations, speakers, text on screen and music rights. The example below illustrates how those layers connect. Further down, a real analysis of launch footage shows what Strata reads from the picture itself.
0.54 – 2.13 s · speaker S1
Dobrý večer z Košíc.
Dobrý0.54 s
večer1.07 s
z1.45 s
Košíc.1.64 s
- enGood evening from Košice.
- whoSpeaker S1, the presenter
- entityKošice: a place, from the lexicon
- screenNEWS 20:00 · KOŠICE
- topicsLocal news · Culture
- shotPresenter · studio
Illustrative SK/EN example, with sample timings. Every layer keeps its start and end in milliseconds. The technology profile and API guide include recorded demo results.
// Illustrative GET /v1/assets/ast_…/timeline, trimmed
{
"items": [
{ "layer": "speech.sentences",
"start_ms": 540, "end_ms": 2130,
"data": { "text": "Dobrý večer z Košíc.",
"language": "sk", "speaker": "S1" } },
{ "layer": "speech.translation.en",
"start_ms": 540, "end_ms": 2130,
"data": { "text": "Good evening from Košice.",
"origin": "model" } },
{ "layer": "speech.entities",
"start_ms": 1640, "end_ms": 2130,
"data": { "text": "Košice", "kind": "place",
"source": "vocabulary" } },
{ "layer": "vision.text",
"start_ms": 0, "end_ms": 10250,
"data": { "text": "NEWS 20:00 · KOŠICE" } },
{ "layer": "speech.topics",
"start_ms": 540, "end_ms": 9770,
"data": { "categories": [
{ "label": "Local news" } ] } }
]
}
01 / Heard
A song is identified
Your audio identification system reports a recording and its ISRC. Strata takes the result in as an event on the programme's timeline.
02 / Matched
The catalogue knows it
The recording connects to the work, writers and publisher in your catalogue. On-screen credits and nearby speech provide context for review.
03 / Reported
The cue sheet writes itself
The programme's cue sheet is generated from the match, reviewed, approved and exported for the rights society, with every change kept in its history.
Launch coverage · 1:25 – 2:44
The picture, read like the soundtrack
- 1:25New shot: a report from the launch pad
- 1:25Logo: Axiom Space · 0.97
- 1:25Rocket 1.00 · tower 0.95
- 1:30Action: smoke rising · 0.97
- 1:39Text on screen: LIFTOFF · 0.97
- 2:30New shot from space: Earth 0.99, spacecraft 0.98
- 2:43Grid fins · 0.93
NASA's public-domain coverage of a crewed launch, read by Strata on a laptop with an 8-billion-parameter vision model. Each confidence is the model's probability of yes against no; what is not in the picture scores near 0.
// GET /v1/assets/ast_…/detections, trimmed
[
{ "timestamp": "00:01:25.875", "type": "shot",
"label": "hard" },
{ "timestamp": "00:01:25.875", "type": "logo",
"label": "Axiom Space", "confidence": 0.971 },
{ "timestamp": "00:01:25.875", "type": "object",
"label": "rocket", "confidence": 0.997 },
{ "timestamp": "00:01:30.775", "type": "action",
"label": "smoke rising", "confidence": 0.969 },
{ "timestamp": "00:01:39.275", "type": "text",
"label": "LIFTOFF", "confidence": 0.967 },
{ "timestamp": "00:02:43.900", "type": "object",
"label": "grid fins", "confidence": 0.931 }
]
