What is text-to-speech (tts)?
Text-to-speech (TTS): Text-to-speech (TTS) is a feature that reads typed text aloud in a synthetic voice, letting you add narration to a video without recording your own. On TikTok, Instagram, and editors like CapCut, creators use TTS to voice captions, deliver lines hands-free, and keep faceless videos moving with audio.
Why creators use text-to-speech
TTS removes the biggest friction point in faceless content: recording your own voice. Type the line, pick a voice, and the video has narration with no mic, no retakes, and no being on camera. The familiar TikTok TTS voices also carry a format signal viewers recognize instantly, which can make a video feel native to the platform. And because the voice reads exactly what you type, your script and your on-screen text stay perfectly in sync.
How to use it well
- Keep lines short. TTS reads punctuation literally, so break long sentences into separate text blocks for natural pauses.
- Spell phonetically when the voice mangles a word. Write it how it sounds, not how it's spelled.
- Pair TTS with on-screen text so sound-off viewers get the same information.
- Don't let TTS carry the whole video alone. Mix it with your own voiceover, music, or b-roll so it doesn't feel robotic end to end.
- Match the voice to the tone. A deadpan TTS voice can land a joke, but it can undercut sincere or emotional content.
Common misconception: TTS is only for lazy or low-effort videos. Used deliberately, it's a legitimate storytelling tool. It can narrate a script faster than you'd record it, deliver dry humor, or keep a series consistent. What reads as low-effort is unedited, monotone TTS with no visuals to support it.
See these signals scored on your own video
ReelTok's AI analyzes your video on-device before you post — one 0–100 virality score built from the signals in this glossary. Free 3-day trial.
Related terms
Browse the full creator glossary, read the growth guides, or try the free virality score checker.