Model reference · open weights

speakerkit-pro

Not for GPU servers Audio argmaxinc Speech→text 1 build Its own licence terms 19k dl/mo

speakerkit-pro is an open-weight audio or speech model from argmaxinc. Built for Apple devices (Core ML). It does not run on NVIDIA GPUs.

What it is

Released byargmaxinc
Released2024-11-25
VRAM242 MB for the weights

What it runs on

Memory and cards for speakerkit-pro (BF16)

242 MBweights, file size
1.6 GBruntime overhead
CardOne streamMemory
RTX 3060 12 GBfits11.6 GB
RTX 4060 Ti 16 GBfits15.4 GB
RTX 3090 24 GBfits23.4 GB
RTX 4090 24 GBfits23.4 GB
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

From the model card

What argmaxinc says about speakerkit-pro

SpeakerKit Pro

Read the blog

Try it on TestFlight

Read the Research Paper to learn more about the architecture and performance benchmarks

Get access here

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Running it

Where it runs

Built for Apple devices (Core ML). It does not run on NVIDIA GPUs.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms