FAQ

wxtts is an AI voice tool platform offering text-to-speech, video dubbing, article narration, and API services. 30+ high-quality voices, supports Chinese and English, designed for creators and developers.

Yes, standard voices are completely free with no registration required, 500 characters per day. Register for more features, upgrade to Creator or Pro for higher quotas and premium voices.

Chinese and English are supported, covering major use cases. More languages are being added.

No. wxtts is a web app, accessible from any browser on desktop or mobile.

Free: 500 chars/day, standard voices. Creator: 30,000 chars/month, premium voices, downloadable audio. Pro: 100,000 chars/month, all features including voice cloning and API. See pricing page for details.

After logging in, go to the Subscription Management page in the dashboard and choose Creator or Pro. Pay securely via Stripe, effective immediately.

Yes, cancel anytime. You keep paid benefits until the current period ends, then automatically downgrade to Free. No auto-renewal after cancellation.

Subscription fees are non-refundable once paid, but you can cancel anytime and keep benefits until the period ends.

Secure payment via Stripe, supporting major international credit and debit cards.

Compatible with OpenAI /v1/audio/speech format. Register, create an API Key in the dashboard, and call per documentation. SDK examples included. Pro plan exclusive.

Yes. 60 requests per minute, 5 per second, max 50,000 characters per request (Pro). Monthly character quota depends on your plan.

Yes. The API endpoint supports streaming audio responses, suitable for real-time narration scenarios.

Yes. Create multiple keys in the API Key Management page, each with its own webhook callback URL.

Premium voices sound more natural, support multiple languages, and are downloadable, ideal for professional content. Standard voices are for quick testing and daily use, using browser built-in speech engine for free users.

Pro plan supports voice cloning. Upload a clear recording to generate a custom voice, perfect for personalized content creation.

Pro subscribers can use generated audio commercially. Free version is for personal non-commercial use only.

Yes. The dubbing tool supports global speed and pitch adjustment, plus SSML tags for fine-grained control (pauses, local speed changes).

MP3 by default, API endpoint also supports other formats. Paid users can download audio files.

Text is used only for the current synthesis, not stored or used for training, destroyed after generation. Your privacy is guaranteed.

Click 'Forgot Password' on the login page, enter your registered email, and reset via the email link. Link is valid for 60 minutes.

After logging in, change your email in Account Settings. A verification email will be sent to the new address, effective after verification.

Yes. Click delete account at the bottom of Account Settings, password confirmation required. All data will be permanently deleted and cannot be recovered.

Yes, Google account one-click login is supported, no separate registration needed.