Detects and tracks which person is speaking across video frames
Specification
most-agreed values
Context
0
Max output
4K
Released
2026-04-16
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
video
Output
text
Price
US dollars per million tokens · most-agreed
Input
free
Output
free
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| nvidia | free | free | — | — | 0 | 4K | — |
More from NVIDIA
most-hosted first