Tavus Griffin (Human Interaction Model)
PricePrice not published
Checked2 October 2026
Where it stands
3newer video generation models since its release
- Gemini Omni 1.2 Flash5 Nov 2026
- FLUX 3 Max19 Oct 2026
- Kling 4.0 (and 4.0 Flash)15 Oct 2026
- Weights
- Closed weights.
How to call it
Where to use Tavus Griffin (Human Interaction Model).
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| 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
First
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’.
‘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.
Notes
Research preview; no public API id or pricing found. Benchmarks: Tavus’s own study plus NVIDIA’s VideoFDB leaderboard (Griffin-Lite).