Help center

How TTSMint works

Clear answers about creating speech, managing Credits, and knowing what to expect.

01

Getting started

Can I try TTSMint before signing in?

Yes. You can preview voices and generate and download short text up to 500 Unicode characters without an account. Guests get two attempts per shared network each day, including failed attempts; the limit resets at 00:00 UTC. Signed-in accounts keep the existing one-time 40 Credits for 30 days.

Which languages and voices are available?

TTSMint currently offers 39 curated voices across English, Simplified Chinese, Japanese, Korean, and Spanish, including adult and child-style profiles. Match the voice locale to your text for the most natural result.

What can I download and adjust?

Generated speech is available as MP3. You can also export SRT or WebVTT subtitles and adjust speed, volume, and pitch before generation.

02

Credits & billing

How are Credits calculated?

With the current voice library, each started block of 100 Unicode characters costs 1 Credit. For example, 250 characters cost 3 Credits. Your balance is reserved before generation and released if generation fails.

Which plans are available, and do Credits expire?

Starter and Pro are monthly subscriptions; their Credits refresh after each successful renewal and do not roll over. The one-time Credit Pack is valid for 365 days. TTSMint uses the Credits that expire soonest first. See Pricing for current amounts and prices.

How do I cancel or manage a subscription?

Open Billing & Credits from your account menu. You can cancel an active subscription at the end of its current billing period or reactivate it before then. Plan switching, payment-method changes, invoices, and self-service refunds are not currently available.

03

Privacy, access & use

Are my text and generated audio stored?

TTSMint has no user-facing audio library or generation history, and text or audio is not written to the Credits ledger. The user-key reader at POST /v1/audio/speech may privately reuse a matching audio result for 300 seconds; that reuse window does not mean the stored object is physically deleted after 300 seconds. Text is sent to the speech service to create audio; minimal account, usage, and billing records are kept to operate the service.

Why do accounts use Credits?

Guest generation has a short-text and shared-network daily limit to protect the service. Signing in gives you account-based generation with the existing Credits balance and billing history. Google sign-in requests basic identity details; email sign-in uses a one-time code. TTSMint never receives a Google or email password.

Can I use TTSMint in my projects or through an API?

You can use TTSMint for personal and creative projects if you have the necessary rights to your content and follow the applicable terms. The hosted service depends on third-party speech channels and has no enterprise SLA. After signing in, create a user API Key under Settings → API access to call the OpenAI-style reader at POST /v1/audio/speech. It shares the account Credits with web generation: each started block of 100 Unicode characters costs 1 Credit. Identical requests with the same key and audio settings can reuse private cached audio for 300 seconds. This does not make the legacy subtitle endpoint or other HTTP endpoints OpenAI-compatible. Open API access in Settings