Model reference · open weights
personaplex is an open-weight audio or speech model from nvidia, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
Specifications
| Maker | nvidia |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 8.4B |
| Variants | 1 |
| Runs with | moshi |
| Based on | kyutai/moshiko-pytorch-bf16 |
| Released | 2025-12-31 |
| Popularity | 131k downloads / month |
| Likes | 2,692 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| personaplex-7b-v1 | 8.4B | BF16 | ~19.3 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys personaplex for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (personaplex below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="personaplex" -F file=@audio.mp3
Details
Languages
Tags
Papers
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗