Aron Kurdish Language Pack

AKLP · Developers

Kurdish Sorani text to speech, for what you build.

Send Sorani text and get speech back, in Aron Fund's own Kurdish voice. Free for personal use, with no tokens to buy. Selling it and commercial use are not allowed.

  • Text to speechKurdish Sorani
  • WAV or MP3One file, or sentence by sentence
  • Free for personal useNo tokens to buy

What you can build

Give what you build a Kurdish voice.

Apps that speak

Let your app read its answers, messages and notifications aloud in Sorani.

Listening instead of reading

Turn articles, lessons and long texts into audio people can listen to.

Access for everyone

Read the screen aloud for people who cannot see it or cannot read it.

Voices that answer

Give your own assistant or personal project a Kurdish voice.

What you get

A voice made for Kurdish Sorani.

  • Our own voice

    A voice trained by Aron Fund for Kurdish Sorani.

  • Reads numbers

    Numbers written as digits are read out as words.

  • Natural pauses

    Each clause is spoken on its own and joined with real pauses.

  • Streaming

    Audio can arrive sentence by sentence, so playback starts early.

  • Your speed

    Slow the reading down or speed it up with one field.

  • Simple to connect

    One request and one header. WAV or MP3 comes back.

Getting started

Three steps to your first sentence.

Create an account

Sign up with your name, email and a password.

Create an API key

Open your profile and create a key. It is shown once, so copy it and keep it somewhere safe.

Send your text

Call the API with the key in the X-API-Key header. The audio comes back as WAV or MP3.

First request

One call, one audio file.

Put your key in place of YOUR_API_KEY, or in ARON_API_KEY, and run it from your app's server. The audio is saved as speech.wav.

curl -X POST https://aklp.aronfund.com/v1/tts \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @body.json -o speech.wav

# body.json (UTF-8)
{"text": "سڵاو، بەخێربێیت!", "format": "wav"}

Reference

The endpoints.

  • POST/v1/tts

    Text in, one complete audio file out.

    API key
  • POST/v1/tts/stream

    The same request, delivered sentence by sentence as each one is ready.

    API key
  • GET/v1/health

    Whether the service is up.

    No key

Request body

text
The Sorani text to speak.
voice
A voice id, or "default".
speed
Reading speed. 1.0 is the voice as tuned.
format
"wav" or "mp3".

Errors

400
The request is wrong: empty text, an unknown voice, or nothing that can be pronounced.
401
The key is missing or not valid.
413
The text is too long.
503
The service is busy or not available. Try again shortly.

Errors come back as JSON: {"error": {"code", "message", "request_id"}}

Good to know.

Terms of use

Free and open for personal use. Selling the service or access to it, and any commercial use, are not allowed.

What it does

It turns Kurdish Sorani text into speech. It is not a chat model and it does not transcribe speech.

Keep the key on your server

Send it from your app's server, never from a web page or an app your users can open up.

If you lose a key

It cannot be shown again. Delete it in your profile and create a new one.

Your usage

Your profile shows how many requests and characters each key has used.

A question about the API?

Write to us and we will answer.