Help

Questions people ask about VocaTTS

Short, specific answers. If yours is not here, email us and a person will reply.

Custom voices

Frequently Asked Questions

Q: What is the difference between voice cloning and voice design?

A: Cloning copies a real person's voice from a 10–30 second recording plus a consent statement read by that same person. Design creates a brand-new voice from a written description of 20–1,500 characters — no recording needed.

Q: Which plan do I need for custom voices?

A: Basic or higher. Basic and Pro include 3 slots, Premium and Studio include 5. Each cloned or designed voice takes one slot.

Q: Where is voice cloning unavailable?

A: Gemini does not yet offer voice cloning in the United Kingdom, the European Economic Area, Switzerland, Illinois or Texas. Voice design is not affected.

Q: Which tools can use my custom voices?

A: Text to Speech, Multi-Speaker, SRT to Audio, AI Dubbing, and PDF to Speech (through Text to Speech). Your voices appear under “My voices”.

Q: Do you keep my recordings?

A: No. The raw recordings are used to create the voice and are not stored. The finished voice is kept by Gemini for up to a year, and you can delete it whenever you like.

Tools

Frequently Asked Questions

Q: How many stock voices are there?

A: More than 1,900 from Google, Microsoft Azure, Gemini and OpenAI. The voice library shows the current count, read straight from the data.

Q: What does SRT to Audio accept?

A: A .srt file up to 2 MB. You can also paste subtitles or turn plain text into an SRT. You get an MP3 timed to each line, plus the edited or translated SRT.

Q: Does VocaTTS transcribe video?

A: No. AI Dubbing starts from an SRT file you already have, then translates it, assigns a voice to each speaker and produces timed audio.

Q: I only need a quick free conversion. Is there something simpler?

A: VocaTTS is built around custom voices and production work. For quick, free text to speech, TTSForFree (ttsforfree.com) is the simpler option.

Credits and payments

Frequently Asked Questions

Q: Can I try it for free?

A: Yes. Guests and free accounts get a small credit allowance to try the stock voices. Custom voices need a paid plan.

Q: Which payment methods are accepted?

A: You can pay with a credit or debit card (Visa, Mastercard, Amex and others) or a PayPal account. Card payments are processed by PayPal, and you do not need a PayPal account to use them. Customers with a Vietnamese bank can also pay through SePay by VietQR or bank transfer, at the plan's VND price. Plans are paid once and do not renew automatically.

Q: Do plans renew automatically?

A: No. Every plan is a single payment. When it ends, you decide whether to buy again.

Q: Why do some voices cost more credits?

A: Gemini, OpenAI and Chirp voices — including cloned and designed voices — cost more per character than standard neural voices. The credit rate is shown next to each voice.

Rights and privacy

Frequently Asked Questions

Q: Can I use the audio commercially?

A: On a paid plan you may use the audio you generate in commercial projects. For cloned voices you must have the right to use that person's voice.

Q: Is my data used to train AI models?

A: On paid plans, no. For guests and free accounts, data may be used to improve service quality.

Q: Can I clone a celebrity's voice?

A: No. You may clone only your own voice or the voice of someone who has explicitly agreed and recorded the consent statement themselves.

Still stuck?

Write to us with your account email and what you were trying to do.