Fixie LogoFixie AI

Building real time speech-to-speech models

Fixie AI models

Fixie LogoUltravox v0.4

LLM
0.4vLLMH100 MIG 40GB

We're building AIs that can communicate as naturally as humans

Human communication is messy. We interrupt, talk over each other, and don't always wait our turn. But this rapid, messy exchange of ideas serves as the backbone of human progress.

LLMs are revolutionary, but their potential impact is currently limited to situations where text-based chat is sufficient.

We think useful, productive, and accessible AGI will require models that can operate in the fast-paced, ambiguous world of natural human communication.

Deploy any model in just a few commands

Avoid getting tangled in complex deployment processes. Deploy best-in-class open-source models and take advantage of optimized serving for your own models.

$

truss init -- example stable-diffusion-2-1-base ./my-sd-truss

$

cd ./my-sd-truss

$

export BASETEN_API_KEY=MdNmOCXc.YBtEZD0WFOYKso2A6NEQkRqTe

$

truss push

INFO

Serializing Stable Diffusion 2.1 truss.

INFO

Making contact with Baseten ๐Ÿ‘‹ ๐Ÿ‘ฝ

INFO

๐Ÿš€ Uploading model to Baseten ๐Ÿš€

Upload progress: 0% | | 0.00G/2.39G