Sautna (صوتنا, "our voice") is the first AI text-to-speech that speaks Sudanese Arabic, trained on real Sudanese speech.

صَوتنا · Sudanese voice AI

Text to speech that actually sounds Sudanese.

Q: Do you support other Arabic dialects?

Sautna is deliberately Sudanese-first; other dialects may follow.

Every Arabic TTS reads Sudanese text like a newscaster from somewhere else. Sautna is trained on real Sudanese speech — the rhythm, the vowels, the warmth. Type something and listen.

56/220

Free demo, no account needed · sign up for 5,000 characters a month.

Or make a voice note and share it on WhatsApp → — you can type in English, it speaks Sudanese.

Hear the difference

Same sentence. Only one of them is Sudanese.

Play both. The first is how Arabic TTS engines read Sudanese text today — stiff, formal, somewhere else. The second is Sautna.

أهلين يا زول! هسع جيت من وين؟ أقعد أشرب معانا شاي.

Why Sautna

Dialect first

Built on the largest Sudanese speech corpus ever assembled, labeled as-spoken — not Modern Standard Arabic with an accent painted on. It says هسع the way Khartoum says it.

Telephony ready

Native 24 kHz audio with 8 and 16 kHz output for IVR and SIP. Sautna voices are already answering real phone calls in production today.

One simple API

One POST request in, a WAV file out. Character-based pricing, no per-minute surprises, and a studio playground for scripts before you ship.

Voices

Meet the voices

ZolLIVE

voice id: zol

Warm, natural Sudanese Arabic — our flagship voice. Conversation, narration and phone lines.

ZolaLIVE

voice id: zola

Bright, friendly Sudanese Arabic — our female voice. Assistants, announcements and phone lines.

Coming soon

Hero voice — studio-recorded. Scale-plan customers get early access.

Your brand's voice, in Sudanese

Custom voices for companies — your host, your announcer, your call-center persona, cloned into a Sudanese voice you own. Join the waitlist for early access.

Developers

Ship a Sudanese voice in five minutes

Authenticate with your API key, send text, get audio back. That's the whole integration. Rate limits and quotas scale with your plan.

Read the API docs

curl -X POST https://sautna.com/api/v1/tts \
  -H "Authorization: Bearer sautna_sk_..." \
  -H "Content-Type: application/json" \
  -d '{"voice": "zol", "text": "أهلين! كيفنك؟"}' \
  --output speech.wav

Where it works

Call centers & IVR

Answer every call in the caller's own dialect. Sautna already runs live on SIP telephony.

Media & content

Narrate news, dub video and voice social content for 50 million Sudanese Arabic speakers.

Apps & education

Give your app a voice users trust — reading assistants, learning tools, accessibility.

Announcements

Turn written notices into spoken audio for radio, events and public services.

Pricing

Start free. Scale when it works.

5,000 free characters a month, no card required. Paid plans from $9/month with full API access and a commercial license.

See plans

Questions

Why does the first request sometimes take a minute?

GPUs scale to zero when idle to keep prices low. The first request wakes one up (~15–60 s); after that, synthesis takes a few seconds. Pro and Scale plans get priority on warm capacity.

What does صوتنا mean?

Sautna is Arabic for "our voice." Sudanese Arabic has been missing from every voice AI — this is the project that changes that: a voice model trained on our own speech, our rhythm, our warmth.

Can I use the audio commercially?

Yes — every paid plan includes a commercial license for the audio you generate. The free tier is for personal and evaluation use.

What formats do I get?

WAV, 24 kHz mono, 16-bit. Pro and Scale can request 8 or 16 kHz output for telephony systems.

Do you support other Arabic dialects?

Sautna is deliberately Sudanese-first. More Sudanese voices are in training; other dialects may follow.