Skip to content

Can you run it?

Pick your machine. We say what works well, what is slow and what will not fit, and how sure we are.

Only the Apple M4 16 GB figures were timed. Everything else is marked estimated or untested, and we would rather say so than guess at a number.

Your machine

Apple Silicon Mac

Windows / Linux with an NVIDIA GPU

Any laptop

Runs well

Apple Silicon Mac, 16 GB, local models only

The whole studio runs offline with no keys. A spoken reply takes about 3 seconds, and the heavy voices are for renders.

On your machine

Works well

  • Live voice agent
  • Cloning in your voice
  • Offline thinking (no internet)
  • Hands-free conversation

Slow or needs extra setup

  • Your voice in Hindi

Won't fit

Nothing: it all fits.

MeasuredMeasured on an Apple M4 with 16 GB, local models only unless the line says Groq.

See every featureNotes per feature, speed, disk space, all machines side by side, and a plain-language glossary

Details for Apple Silicon Mac, 16 GB, local models only.

What works

  • WorksLive voice agentfull spoken reply 3.1 s
  • WorksCloning in your voicevoice built in 2.4 s
  • Works with limitsYour voice in Hindi30 to 40 s per sentence on the CPU, measured; renders, not live calls
  • WorksOffline thinking (no internet)Llama 3.2 3B on the Apple GPU
  • WorksHands-free conversationfirst audio in about 1 s

Switch off, or use the cloud for

  • Run ./auralis warm before a demo so the first reply is about 3 s instead of about 18 s.
  • Use Chatterbox (your voice in Hindi) for Studio renders. Keep live calls on Kokoro voices.

Phone calls (through Vobiz, not yet tested live) and meeting booking with Google Calendar (tested live) use the same live agent, so they work wherever "Live voice agent" works. Phone calls also need an internet address that Vobiz can reach, and they sound best with a preset voice because cloned voices pause between sentences. WhatsApp voice notes are built but not yet tested live.

Expected speed and memory

Full spoken reply (median)

3.1 sMeasured

English 2.1 s, Hindi 4.1 s; 30 spoken questions, local models only

First audio (median)

1.0 sMeasured

Voice clone built

2.4 sMeasured

warm, consent check included

Your voice in Hindi

about 30 to 40 s per sentenceMeasured

Chatterbox on the CPU: for Studio renders, not live calls

Memory with every model loaded

10 to 12 GBMeasured

16 GB works but swaps under heavy use

Disk space

Core install on disk

about 15 GBMeasured

10.6 GB of models (embedding model 4.3 GB, Qwen3-TTS 2.3 GB, local language model 1.7 GB, Whisper 2.0 GB, Kokoro 0.3 GB) plus 4.1 GB of Python environments.

Add Chatterbox (--chatterbox)

about 4.3 GBMeasured

3.0 GB model plus a 1.3 GB environment, read on the M4; the same files on any machine.

All machines side by side

Showing local models only. Your pick is outlined.

Which capabilities each machine supports, with local models only.
MachineLive agentCloningHindi cloneOffline thinkingHands-free
Mac 8 GBEstimatedTier: BasicWorks with limitsWorks with limitsWorks with limitsWorks with limitsNot practical
Mac 16 GBMeasuredTier: Runs wellWorksWorksWorks with limitsWorksWorks
Mac 24 GB+EstimatedTier: Full studioWorksWorksWorks with limitsWorksWorks
NVIDIA 4 GBUntestedTier: BasicWorks with limitsWorks with limitsWorks with limitsWorks with limitsNot practical
NVIDIA 6–8 GBUntestedTier: Runs wellWorks with limitsWorksWorks with limitsWorksWorks with limits
NVIDIA 12 GB+UntestedTier: Full studioWorksWorksWorks with limitsWorksWorks
CPU onlyEstimatedTier: BasicNot practicalWorks with limitsWorks with limitsNot practicalNot practical
  • works well
  • works with limits (slow, swaps memory, or needs extra setup)
  • not practical on this machine
  • Measuredtimed or sized on a real machine by this project
  • Estimatedworked out from model sizes or research notes, not run on this hardware
  • Untestedno one has run auralis on this hardware yet

Words used here, in plain language

Groq
A free online service that listens to the caller and thinks of the answer, so your computer only has to speak it. Needs internet and a free key.
Local models
The AI runs on your own computer, with no internet. Nothing leaves the machine, but it needs more memory.
Kokoro
The small ready-made voice that talks during live calls and chats. Fast, and runs even without a graphics card.
Chatterbox
Clones your own voice in Hindi, from a sample you agreed to give. Tens of seconds per sentence, so it is for finished audio, not live calls.
Render
Making a finished audio file you can play later, instead of talking live.
Swapping
When a computer runs out of memory and borrows disk space. It still works, but everything gets slow.
VRAM
The memory on a graphics card. AI voices and models have to fit in it to run fast.
Offline thinking
The agent can work out answers with no internet by using an AI model stored on your machine.
Measured, estimated, untested
Measured means we timed it on a real machine. Estimated means we worked it out from model sizes. Untested means nobody has run it there yet.

Minimum: any 8 GB laptop with a free Groq key. Recommended: Apple Silicon 16 GB or an NVIDIA GPU with 6 GB+.

Setup steps, the optimisation research and the trial report with the measured numbers are in the project's docs, shared on request.