Studio
Log in Sign up Try the API

GETTING STARTED

  • Introduction
  • Our models
  • Integration
    • First API call
    • Models and pricing
    • Error codes
  • Glossary
  • Changelog

FEATURES

  • Features
    • OCR
    • Audio & Transcription

DEPLOYMENT

  • On-Cloud
  • On-Premise
  • On-Device
API status ⚠️
Docs API Playground Dashboard
Log in Try the API
GETTING STARTED > OUR MODELS

Our models

Explore the capabilities and performance metrics of our sovereign models to pick the right solution for your business.

FEATURED MODELS

On-Cloud
On-Premise

AlphaDigit Max

Multilingual OCR for printed and scanned documents. Robust handling of complex layouts.

1.0
On-Cloud
On-Premise

AlphaAudio v1

High-accuracy ASR optimized for French. Fast and efficient audio stream transcription powered by our ELM architecture.

1.0

GENERALIST MODELS (2)

On-Cloud
On-Premise

AlphaDigit Max

1.0

Multilingual OCR for printed and scanned documents. Robust handling of complex layouts.

On-Cloud
On-Premise

AlphaAudio v1

1.0

High-accuracy ASR optimized for French. Fast and efficient audio stream transcription powered by our ELM architecture.

SPECIALIZED MODELS (1)

AUDIO
OCR
On-Premise
On-Cloud
On-Device
CPU CPU
GPU GPU

OCR (1)

AlphaDigit Handwritten

1.0

Model specialized in recognizing handwritten words or sentences in French and English, from text regions (bounding boxes) produced by a Layout step.

Écriture manuscrite
< Introduction
🤗
Integration >