From Ethiopia. For the way we speak.

Language AI,
built for here.

Turn spoken words and document images into text, and your knowledge into useful answers.

Speech, Amharic OCR, language models, and AI assistants with an Ethiopian language focus. Built to become part of your product.

Explore the tools. Bring us your language challenge.

The language workspaceIllustration
A thought, in your own words

ሰላም፣ እንዴት ነህ?

AmharicSpeech input
Text you can work with

Capture. Understand. Respond.

Our language focusአማርኛ AmharicAfaan OromooEnglish Text workflowsExplore capabilities

The product toolkit

From words.
To a useful next step.

Start with one capability. Connect speech, document recognition, generation, and retrieval as your product grows.

Speech to text

Make every word usable.

Dictate into an editable transcript for notes and search. Select English, Amharic, or Afaan Oromo where your browser supports it.

Explore the tools
Try dictation

Text to speech

Give your words a voice.

Explore spoken interfaces, narration, and read-aloud experiences with an Ethiopian language focus.

Available device voices
Try read aloud

Text tools

Put language to work.

Turn long notes into concise extracts, and explore language workflows for your application.

Explore the tools
Summarize text

Document retrieval

Answers with a source.

Search a document with a question or keywords and find relevant passages with references to the source.

Explore the tools
Search a document

Amharic OCR

Bring Ethiopic script into text.

Extract printed Amharic and English text from document images for editing, search, and knowledge workflows.

Explore the tools
Try image to text

Image extraction supports printed Amharic and English. Speech languages and voices depend on your device. Discuss your language and document requirements with our team.

A place to explore

Your words.
Something useful.

Read an image, listen to your words, shorten a document, or find the passage you need. Bring your own input or start with an example.

Try it now
Read a document image

Extract editable text from a printed Amharic or English image.

PNG, JPEG or WebP. Up to 8 MB and 16 million pixels. Clear, printed text works best.

Your image is processed on your device. Language resources download on first use.

Extracted textReady

Choose an image or use an example to begin.

Your result will appear here.

Start with public or sample material. How your data is handled.

For people who build

Start with
working tools.

Use the playground's text utilities in your own projects.

  • Select key sentences from a document
  • Find source passages for a question
  • Compare a transcript against a reference
JavaScriptText utilities
import {
  summarizeText,
  searchDocument
} from './text-tools.mjs';

const document = `
The library opens at 9 AM on weekdays.
Members can borrow books for two weeks.
The library closes at 5 PM.
`;

const summary = summarizeText(document, 2);
console.log(summary.text);

const passages = searchDocument(
  document, 'When does the library open?'
);
console.log(passages);

Save the downloaded module alongside your script. Runs in modern browsers and Node.js.

Measure what matters

Compare your
transcript or OCR.

Paste the expected text and your result to calculate word and character error rates for that pair.

Up to 3,000 characters and 750 words per field. Empty output is counted as deleted reference text.

How the comparison works

Word error rate counts word substitutions, deletions, and insertions, divided by the number of reference words. Character error rate applies the same calculation to characters. Lower is better; insertions can push an error rate above 100%. Comparisons normalize Unicode, letter case, and whitespace. Word comparisons ignore punctuation; character comparisons include it. These results measure only the text pair you provide.

About EthioNeural

Built here.
Open to what comes next.

EthioNeural develops speech, document recognition, and language AI products with a focus on Ethiopian languages and the people who use them.

We bring open models, careful evaluation, and application engineering together. Our goal is to help teams turn language technology into something people can use every day.

Explore the public tools, then work with us on your language and document requirements. We build with upstream open models, browser capabilities, and application engineering.

Founder inquiries

Product conversations, demos, and partnerships.

founder@ethioneural.com

General inquiries

Questions, feedback, and support.

contact@ethioneural.com

Let's build something useful

Bring us your
language challenge.

Tell us what you want to build. We will discuss a demo, model fit, and the path to API access.

founder@ethioneural.com

For other questions:
contact@ethioneural.com

Opens your email app with a draft. Nothing is submitted automatically. Please leave out passwords and sensitive data.