FAQ

The questions we are asked most often about Voice Factory TTS. If this is your first visit, read it alongside How to use.

Using the service

Is it really free?

Yes. No account and no payment — you can start right away. Server costs are covered by the ads on the site.

Do I need an account?

No. We do not collect names or contact details; a random per-browser identifier is used only so you see the files you made.

How much can I make per day?

50,000 characters per person (per browser) per day. Previews and finished files both count against it, and it refills at midnight (KST). What is left is shown in the Create panel on the main screen.

How much text can I submit at once?

Up to 10,000 characters at a time. For longer writing, make it chapter by chapter or paragraph by paragraph.

Does it work on a phone?

Yes. It works the same in a phone browser, with a Create button pinned to the bottom of the screen. Finished files download straight to the phone.

Do previews count against my allowance?

Yes, but a preview reads only the first 200 characters, so it uses very little.

Files

How long are my files kept?

They are deleted automatically after 24 hours. Download anything you need right after making it.

I cannot see my files on another device.

In exchange for not requiring an account, files are tied to the browser. Download them on the device that made them and move them across. Clearing your browser cookies also hides the earlier list.

Which file type should I choose?

mp3 is the safe default. Choose wav to edit with no quality loss, or m4a for use on an iPhone. If phone hardware or a particular program demands a type, follow that.

Can I download several files at once?

Tick the files in the results list and press "Download selected as zip" — the audio and subtitles come down as a single zip.

Voices

Can I use the audio commercially?

Speech synthesis is performed by outside services (Google, Microsoft), and how far their synthetic voices may be used commercially depends on their own policies, so Voice Factory cannot guarantee it. Check the relevant policy before using the audio in advertising or anything you sell.

How do I add a pause in the middle?

Repeated spaces and blank lines have no effect — they collapse into one space during conversion. Use a comma (,) for a short breath, a full stop (.) for a sentence breath, and an ellipsis (…) for a slightly longer pause. If you need an exact number of seconds, switch to Script mode and set Gap between lines to 0–2 seconds; that much silence is inserted after each line. Writing several lines under the same name keeps it in one voice. Writing for TTS covers this in detail.

The pronunciation sounds wrong.

Under "Pronunciation fixes" on the main screen, register the written form and how it should sound — "NH → 엔에이치", for example — and it is read that way. For numbers, dates and symbols, writing them out in words (see Writing for TTS) makes them accurate.

Can you add more voices?

The set of voices is fixed, but combining tone (speed, pitch, volume) with effects (child, elder, robot, phone, echo and so on) can make the same voice sound completely different.

Can several people speak in one file?

Yes. In "Script (several)" mode on the main screen, write "Name: line" and each character is read in their own voice and merged into one file. See Dialogue audio for the full method.

Does it read English or other languages?

Voices marked "multilingual" in the list read English and several other languages. Language-listening material has worked examples.

Can I only pick one voice at a time?

Yes — in one-voice mode you pick a single voice. Compare a few with ▶ first, and if you want another version, change the voice and create it again. For people speaking in turn, use Script mode.

What about text longer than 10,000 characters?

Split it by chapter or section and make several files. Numbering the file names 01, 02 and so on keeps the order clear. Making an audiobook explains the approach.

Subtitles & music

How do I get the subtitle file?

Once the audio is made, a CC button appears in the results list. Pressing it downloads an SRT subtitle file timed to the sentences. Most video editors and YouTube can import it.

Is the background music free of copyright?

"Calm music", "Rain" and "Waves" are generated on the server itself, so no separate music rights apply. For music you upload under "My music", you must hold the right to use it.

What music files can I upload?

mp3, m4a, wav, ogg, aac and flac, up to 15MB. Uploaded music is kept for 24 hours and then deleted automatically.

Privacy

Is my text stored?

Your text is sent to an outside speech server to be spoken, and is deleted from the Voice Factory server as soon as the conversion finishes. The beginning of the text, used as the file title, is kept alongside the result for 24 hours. Do not enter personal or sensitive information. The Privacy policy has the detail.

What do the visit statistics collect?

Visitor counts and usage are tallied on this server itself. Nothing is sent to an outside analytics company. Device type, operating system, browser and only the domain of the referring site are recorded; search terms and the text you enter are not collected. You can switch it off at any time under "Visit-statistics settings" at the foot of the page, and it turns itself off if your browser sends a GPC signal. The Privacy policy has the detail.

Troubleshooting

It says "Too many requests".

Sending a lot in a short time blocks you briefly. It keeps the server shared fairly — try again in a minute or two.

It says "The service is busy right now".

The number of jobs handled at once is capped to keep the server healthy. Trying again shortly almost always goes straight through.

It says the conversion failed.

This happens when the link to the outside speech server is briefly unstable. Try again shortly. If it keeps failing, send us the beginning of your text and the settings you chose and we will look into it.

Not finding your answer?

hipal@naver.com — write to us. Feature ideas are welcome too.