Post-Cutoff

TavusGriffin familyPreviewVideo generationReleased 1 Oct 2026

Tavus Griffin (Human Interaction Model)

PricePrice not published

Checked2 October 2026

Where it stands

3newer video generation models since its release

All video generation models

Weights
Closed weights.

How to call it

Where to use Tavus Griffin (Human Interaction Model).

Providers, model ids, endpoints and docs for Tavus Griffin (Human Interaction Model)
ProviderModel idEndpointDocs
Tavus (research preview) tavus.io

Pricing

Price not published.

No price source linked. Checked 2 October 2026.

Specs

Input
Video and audio
Output
Video and audio
Context window
Not published
Max output
Not published
Open weights
No
Licence
Proprietary
Released
1 October 2026
Status
Preview
Type
Video generation

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Full-duplex face-to-face video conversation

    Video-to-video model that sees and hears the user while speaking, interrupts and takes interruptions, and reacts to gestures and objects in real time; Tavus calls it the first ‘Human Interaction Model’.

    Source: tavus.io

  • ‘Video Turing test’ result (vendor study)

    48% of 54 participants in 1-minute blind live calls judged it human (Tavus’s earlier stack ≤2%); NVIDIA VideoFDB generation 3.83/5 vs human 3.92; median latency ~1.9 s.

    Source: tavus.io

Notes

Research preview; no public API id or pricing found. Benchmarks: Tavus’s own study plus NVIDIA’s VideoFDB leaderboard (Griffin-Lite).