Small.
Edge.
Voice AI.

The Only CPU-First Voice AI

Most voice AI platforms run every layer - STT, LLM, and TTS - through separate GPU-backed cloud APIs, stitched together client-side. Each hop adds network latency on top of GPU inference cost, and nobody owns the seams where turn-taking and barge-in actually happen.

We took a different approach for the layers that matter most for latency and cost. GateTurn (turn-taking & barge-in), Psst (noise suppression), and Versa (TTS) are trained from scratch and hand-optimized for ARM and x86 CPUs - no GPU overhead, full control over quality and latency. STT and LLM run on best-in-class low-latency providers, orchestrated through our own Go pipeline instead of stitched together client-side.

The same cascade architecture, rebuilt model by model for maximum efficiency. ~1.3s voice-to-voice, running entirely on CPU - no GPU fleet required.

Our models are trained on MareNostrum 5, one of Europe's most powerful supercomputers, through the Barcelona Supercomputing Center AI Factory program. We work closely with NVIDIA (Inception partner) and AWS to push CPU-based inference to its limit. This is European deep tech - building voice AI infrastructure from the ground up.

Real-World Applications

Developer First

Integrate Lokutor in minutes with our SDKs and comprehensive documentation.

import { VoiceAgentClient, VoiceStyle, Language } from '@lokutor/sdk';

const client = new VoiceAgentClient({
  apiKey: 'your-key',
  prompt: 'You are a helpful and friendly AI assistant.',
  voice: VoiceStyle.F1,
  language: Language.ENGLISH,
  visemes: true,
});

client.on('transcription', (text) => console.log('You:', text));
client.on('response', (text) => console.log('Agent:', text));
client.on('visemes', (visemes) => animateMouth(visemes));
client.on('status', (status) => console.log('Status:', status));

await client.startManaged();

from lokutor import VoiceAgentClient, VoiceStyle, Language
import os

client = VoiceAgentClient(
    api_key=os.environ['LOKUTOR_API_KEY'],
    prompt='You are a helpful and friendly AI assistant.',
    voice=VoiceStyle.F1,
    language=Language.ENGLISH,
)

@client.on('transcription')
def on_transcription(text):
    print(f"You: {text}")

@client.on('response')
def on_response(text):
    print(f"Agent: {text}")

@client.on('status')
def on_status(status):
    print(f"Status: {status}")

client.start_conversation()

Get Started

Try the world's most efficient voice AI platform. Pick a voice and start a conversation right now - no sign-up required.

Or reach us directly at contact@lokutor.com