FAQ & Support

Last updated: 2026-08-10

What is SastaSpeech?

An expressive AI text-to-speech service for creators worldwide. Type a script, get studio-quality narrator audio in seconds.

What languages do you support?

Dozens of languages — including English, Spanish, French, German, Hindi, Portuguese, Arabic, and many more — powered by ElevenLabs v3, with natural, expressive prosody in each.

How long does a generation take?

Typically under 10 seconds end-to-end: a couple of seconds for text refinement (Gemini), a few more for voice synthesis (ElevenLabs).

What's the difference between plans?

Each plan has three caps: max characters per request, generations per day, and total characters per month. See the upgrade picker in-app for full details. Day passes are one-time top-ups that ADD to your current plan without replacing it.

Are the generated audios commercial-use?

Yes. You own the audio output and can use it in commercial projects (YouTube monetisation, paid courses, etc.). See Terms Section 7.

How long are audio files kept?

Up to 24 hours, max 5 files per user. Download anything you want to keep — files auto-delete after that.

Can I get a refund?

Yes, if you haven't used any credits and the request is within 7 days of payment. See Refund Policy.

How do I upgrade my plan?

Click "Upgrade" in the top bar after signing in, pick your plan, and pay securely via Razorpay. Your new limits go live the moment payment is confirmed.

Why does my generation say "Daily limit reached"?

Every plan has a daily cap (a rate-limit, not a quota). Wait 24 hours or buy a one-time top-up for +3 generations.

Can I clone my own voice?

Not yet — currently only the curated voice library is available. Custom voice cloning is on the roadmap.

Is my data used to train models?

No. Your scripts and generated audio are never used to train any model. See Privacy Policy.

Still stuck?

Email support@sastaspeech.com or use the Contact page.