About

Voice Factory TTS is a free web tool that reads your text aloud in a human voice and hands you the audio file. No install, no sign-up — it runs in the browser.

Why it exists

Recording a single line of announcement, or one piece of narration for a presentation, usually means setting up equipment or hiring a voice actor. Free TTS services, meanwhile, often let you audition only one voice at a time, make downloading awkward, or cannot produce a conversation between several speakers at all.

Voice Factory started from one idea: if you have the words, you should be able to walk away with usable audio in a few minutes. Features are added around the jobs people actually bring here — phone greetings, teaching material, video narration.

What it does

• Many voices — Korean voices, plus multilingual voices that also read Korean.
• Tone and effects — tones such as news, calm, soft and phone-system, combined with child, elder, robot, phone and echo effects.
• Script mode — a script written as "Name: line" is read with a different voice per character and merged into one file.
• Subtitles (SRT) — a time-aligned subtitle file is produced alongside the audio, ready to drop into a video.
• Pronunciation fixes — make a mis-read word sound right while the subtitles keep the original spelling.
• Background music — calm music, rain or waves generated on the server, or a track you upload yourself.

How it is run

• No accounts. We never ask for your name or contact details. Users are told apart only by a random per-browser identifier.
• Nothing kept. Your text is removed from the server once the audio is made, and the files are deleted automatically after 24 hours.
• Shared fairly. A daily allowance keeps one limited server usable by everyone.
• Said plainly. That speech synthesis uses outside servers (Google, Microsoft), that visits are counted, and that ads may appear, are all written out in the Privacy policy.

Rules of use

Anyone may use Voice Factory, but not for the following.

• Impersonating a real person or organisation, or deceiving people — phone scams and the like.
• Producing audio that defames someone or promotes hatred or discrimination.
• Reading out and distributing copyrighted books, articles or lyrics without the rights holder's permission.
• Sending bulk automated requests that get in the way of other users.

Whether the audio you make may be used commercially depends on the speech provider's own policy, so this service cannot guarantee it. Check the relevant policy before using it in advertising or anything you sell.

You are responsible for the text you submit and for the rights to it. The full list of prohibited uses is in the Terms. If you come across a violation, write to the address below. Confirmed cases have their access blocked.

Voice Factory is an individually run service with no partnership, sponsorship or endorsement from Google or Microsoft. Those names appear only to state which technology is used; each trademark belongs to its owner.

Who finds it useful

• YouTube creators who would rather not use their own voice.
• Small business owners making their own phone greetings and store announcements.
• Teachers and trainers adding narration to course material.
• Writers and bloggers who want to hear their own work as an audiobook.
• Language learners and their teachers who need material to repeat after.

What's next

Features keep being refined around what users ask for. If something is missing, awkward, or read wrongly, say so — it goes into the next round of changes.

Contact

Send feature ideas, bug reports and partnership enquiries to the address below.

hipal@naver.com