# Text to speech (TTS)

> Text to speech, or TTS, is the technology that converts written text into spoken audio, producing a narration track from a script without anyone recording it.

Canonical: https://www.makeviral.ai/glossary/text-to-speech
Updated: 2026-09-15
Published: 2026-09-15
Author: MakeViral Team (https://www.makeviral.ai/about)
Publisher: MakeViral (https://www.makeviral.ai)

**Definition:** Text to speech, or TTS, is the technology that converts written text into spoken audio, producing a narration track from a script without anyone recording it.

TTS is the engine behind an [AI voiceover](https://www.makeviral.ai/glossary/ai-voiceover). The two terms get used interchangeably, but they are different levels of the same thing: TTS is the underlying conversion, and a voiceover is what you do with it in a video.

## The two kinds you will meet

- **Platform TTS.** TikTok's own in-app voice, applied to on-screen text. Free, instantly recognisable, and locked to a small set of voices.
- **Model TTS.** A speech model called through software, producing a downloadable audio file with per-word timing. More control, more voices, and usable in any editor.

The recognisable platform voices carry a format signal of their own. Viewers know what kind of video they are about to watch before a word finishes.

## Getting a clean read

- **Write for the ear.** Short sentences, no subordinate clauses, no parentheses.
- **Spell out the traps.** Numbers, dates, acronyms and brand names are where TTS mispronounces. Write "twenty twenty six" if the model says "two thousand twenty six".
- **Punctuate for pacing.** Commas and full stops are the only pause controls most models expose.
- **Read it back once.** A sentence that sounds fine to read can be unspeakable aloud.

## Where it fits in the pipeline

Script, then TTS, then captions built from the returned timings, then the render. Getting that order right is what keeps the words on screen in sync with the voice. See [auto captions](https://www.makeviral.ai/glossary/auto-captions).

MakeViral runs this pipeline end to end from a prompt. See the [AI voiceover video generator](https://www.makeviral.ai/tools/ai-voiceover-video-generator).

## Questions about text to speech (tts)

### What is the difference between TTS and an AI voiceover?

TTS is the technology that turns text into audio. An AI voiceover is the finished narration track in your video, produced by TTS and then timed, levelled and paired with captions. In practice people use the words interchangeably, but one is the engine and the other is the output.

### Why does TTS mispronounce words in my script?

Usually because of numbers, acronyms, names and units, which have no single correct reading. The fix is to spell the word phonetically in the script, write numbers out in full, and break an acronym into letters with spaces or full stops between them.

### Is TikTok's built-in TTS voice free to use?

It is available inside the app at no cost for personal use, and it is applied to text you add to a video. Its limits are the small voice selection and the fact that you cannot export the audio, so creators working outside the app use a separate speech model instead.

## See it in action

- [TikTok Voice Generator for AI Voiceover Videos](https://www.makeviral.ai/tools/ai-voiceover-video-generator): The narrator-over-gameplay format: a written script becomes a voiced, captioned vertical video with a background clip, in one pass.

## Related terms

- [AI voiceover](https://www.makeviral.ai/glossary/ai-voiceover): An AI voiceover is narration produced by a speech model from a written script, used in place of a recorded human voice, and usually returned with per-word timing that captions can be built from.
- [Auto captions](https://www.makeviral.ai/glossary/auto-captions): Auto captions are subtitles generated automatically from a video's audio by speech recognition, or from the script that produced the audio, rather than typed and timed by hand.
- [Full glossary](https://www.makeviral.ai/glossary)