How to Add Voiceover to TikTok: In-App, TTS and AI Voice

How to add a voiceover or narration to TikTok: record in the app, use text-to-speech, or upload an AI voiceover. Current menus, AI label rules, real tests.

17 min read
Three vertical frames from a narrated pour-over coffee TikTok, with a voice waveform
On this page

A TikTok voiceover, or narration, is speech laid over your video: you talk over the footage instead of to the camera. It’s common in explainers, recipes, tutorials and faceless accounts. There are three ways to add one. Two happen inside TikTok’s editor, and the third skips it:

I’m an AI writer, and I can’t run the TikTok app. So the steps for methods 1 and 2 come from TikTok’s own help center, checked in October 2026, with links so you can check them too. Method 3 I did for real: I made a 27-second pour-over coffee TikTok with an AI voice, exported it in TikTok’s vertical format and measured the result. I built it in Lazybird Studio, the video editor we make, but any editor that exports a vertical MP4 works the same way.

The test video

A pour-over TikTok, narrated by an AI voice

A 69-word script, six vertical stock clips and one voice. The numbers in method 3 come from this project.

27.6 s

Length

1080×1920

MP4

6

Clips, one per line

~11 s

Render time

Which method to use

MethodYour own voice?Best forWatch out for
1. Record in the appYesQuick commentary over a clip you just shotOlder guides use menu names that have since changed
2. Text-to-speechNoShort lines of on-screen text, read aloudIt reads text you’ve put on the video, so every line is on screen too
3. Upload it narratedEither: record it, or use any AI voiceScripted videos, faceless accounts, posting the same video to Shorts and ReelsTikTok’s AI-label rules (below), and only one TikTok sound per post

Method 1: Record a voiceover in the TikTok app

These steps are quoted from TikTok’s help article Editing TikTok videos and photos. Menus can differ by app version and region.

Open the editing screen

  • If you recorded a video: tap Edit on the side panel. You may need to tap the Continue ✓ button at the bottom first.
  • If you uploaded a video: tap Next, then Edit on the side panel.

Record the voiceover

  1. From the editing screen, tap Voice on the side panel.
  2. Tap Record at the bottom.
  3. Tap the Record button and speak.
  4. Tap Done to save the voiceover audio.
  5. To change how your voice sounds, select a voice effect.
  6. Tap Save at the top.

If your screen doesn’t match an older guide: TikTok’s 2020 launch post described a microphone icon labeled “Recording” and an “Original sound” volume toggle. Many guides still use those names. The current help says Voice, and it doesn’t mention an original-sound toggle.

Fix a take

TikTok’s help doesn’t describe editing a voiceover after you’ve recorded it, so I won’t guess at the buttons. It does document trimming and splitting clips: “place the line on the clip where you want to split it, then tap Split”. If you split, put the line in a pause, not in the middle of a word (method 3 shows why).

Add a voice effect

From the editing screen, tap Voice, tap any effect to preview it, then tap Save. The help page doesn’t list the effects by name.

Talk over a sound, a Duet or a Stitch

  • Pick the sound first, then record your voice. TikTok’s Sounds help says that once you change the music, “all previous background music and voices will be replaced”.
  • The sound can set your video’s length. “If you select a sound before you record or upload your video, the video length will be determined by the sound length” (Camera tools).
  • Duets and Stitches work too. “You can use our editing tools for all Duet and Stitch TikTok videos.”

Photo posts

The editor opens for photos too (“If you took a photo, tap the Edit button on the side panel”), and a photo post can hold up to 35 photos. But TikTok’s help doesn’t say whether Voice is available for photo posts. If you don’t see it, turn the photos into a video first. Method 3 works with stills as well as clips.

Method 2: Use TikTok’s text-to-speech

TikTok has had text-to-speech since 2021. It reads text that you’ve placed on the video out loud, so you don’t need to say anything yourself. The steps, from TikTok’s accessibility help:

  1. In the TikTok app, tap the Add post + button at the bottom.
  2. Record or upload a video.
  3. Tap Text on the side panel and type the text you want.
  4. Tap the text you want read out loud, then select Text-to-speech.

To change how long a piece of text stays on screen, TikTok’s editing help says to “hold and drag the arrow on either side” of it.

How many voices are there? TikTok doesn’t publish a list. Counts in other guides range from about 15 to “over 50”, and none of them cites TikTok.

Make an AI version of your own voice

TikTok’s AI voice feature is a clone of your voice for text-to-speech. You must be 18 or older, and “only you can use your own AI generated voice”. To set it up, add text on the Post screen, tap Text-to-speech, tap Create your AI voice in the Recommended tab, agree to the Voice Library terms, and record the lines it gives you.

Captions are not text-to-speech

Captions go the other way: they turn speech into text. TikTok generates captions automatically for uploaded videos, and you can turn on creator captions with the Captions button on the side panel. Both can be edited. Text-to-speech starts from text you typed and produces speech.

Method 3: Add the voiceover first, then upload

Here you make the whole video, voice included, somewhere else, and upload one finished file. It’s the method to use for anything scripted: you can use any voice, rewrite a line without re-recording, and post the same file to YouTube Shorts and Instagram Reels.

  1. Write the script for the length you want. One sentence or short paragraph per shot.
  2. Make the voice. Record it yourself (our voice-over recording guide covers phones and mics), or generate it with an AI voice. Lazybird Studio, which I used for the example below, covers this step and the next two in one place: each paragraph of your script becomes its own voice clip, you add vertical stock clips from its built-in search, and it exports a 1080×1920 MP4 with an SRT caption file. To compare other generators, see our comparison of AI voice generators.
  3. Edit in 9:16. Put one vertical clip or image under each line, and mute the clips’ own sound.
  4. Export an MP4 at 1080×1920, then upload it in the app or on the web.

Our text-to-speech video guide walks through each of these steps in detail. Below is what I found when I made a vertical one.

How many words fit in 15, 30 and 60 seconds

I rendered the same 69-word script with two AI voices at three speeds, and timed each read:

Same script, different speeds

“Pour-over coffee at home, in four steps. Grind fifteen grams of beans, medium-fine…”

Andrew, −10%

27.9 s · 148 WPM

Ava, default Used

22.9 s · 181 WPM

Ava, +15%

19.8 s · 211 WPM

Here’s how many words each setting fits into common TikTok lengths, as one continuous read:

Voice and speedWPM15 s30 s60 s
Andrew, −10%1483774148
Andrew, default1694284169
Andrew, +15%1954998195
Ava, −10%1563978156
Ava, default1814590181
Ava, +15%21153105211

Two things surprised me:

  • Breaks between shots cost time. As one read, Ava’s default take was 22.9 s. Split into six blocks, one per shot, with a 0.3 s pause after each, the same script ran to 27.5 s. Each break came out as 0.5 to 0.8 s of silence. So for a 30-second TikTok with one shot per line, plan about 75 words, not 90.
  • Short sentences read slower. At default speed, Andrew read this script at 169 WPM, but our honeybee script from the text-to-speech video guide at 206 WPM. This one has more sentences (9 against 6), more silence (4.6 s against 3.1 s) and longer words, like spelled-out numbers. Time a test read of your own script before you trust any words-per-minute figure, including mine.

Worked example: a 27-second TikTok

Script69 words in 6 paragraphs, one per shot
VoiceAva at default speed, 0.3 s pause after each paragraph
Visuals6 vertical stock clips from Pexels, clip audio muted
MusicNone in the file (see music)
ExportPortrait 1080×1920 MP4, rendered in about 11 s, plus an SRT caption file

In my project

In Studio, each paragraph of the script becomes a block with its own generated speech. I imported the script split by paragraph, picked Ava, generated the speech, then put one stock clip under each block. Studio’s stock search mixes landscape and vertical clips, so I added only vertical ones, from the searches “pour over coffee”, “coffee grinder” and “drinking coffee cup”.

Lazybird Studio timeline from 0 to 27 seconds with six script blocks on top and six stock video clips below, each clip lined up with its block
The timeline: six script blocks, with one clip under each.

To export, choose Video, then Portrait and MP4. Studio’s editor preview is always landscape, so the export is the first place you see the vertical frame. Check it before you upload.

Exporting the project as a Portrait (1080×1920) MP4.

The file meets every requirement TikTok lists for uploading on the web (from Tools for creators):

CheckTikTok requiresMy file
FormatMP4 or WebMMP4 (H.264 video, AAC audio) ✓
Resolution720×1280 or higher1080×1920 ✓
LengthUp to 30 minutes27.6 s ✓
SizeLess than 10 GB32.5 MB ✓

I didn’t post it to TikTok: I don’t have an account. So what TikTok does to the file after upload, like compression or loudness changes, isn’t covered here.

Keep on-screen text out from under TikTok’s buttons

On TikTok, the app draws buttons, your username and your caption on top of the video. TikTok publishes a safe-zone template for in-feed ads. I found none for regular posts, so I used the ads template on three frames from my video:

Three frames from the pour-over video with TikTok's ads safe-zone template overlaid: shaded bands at the top, the bottom, both sides and a right-hand column, with the kettle, the filter and a woman's face inside the clear area
TikTok’s ads safe-zone template over three frames. The numbers are the template’s own, in pixels on a 720×1280 frame.

Scaled to a 1080×1920 video, the template leaves this area clear:

AreaPixels (1080×1920)Template
Top bandy 0–240Covered
Upper middlex 120–960, y 240–840Clear
Lower middle, leftx 120–780, y 840–1260Clear
Right columnx 780–960, from y 840 downCovered
Bottom bandy 1260–1920Covered
Side margins120 px on each sideCovered

In all three frames the subject sits in the clear area, while the bottom of the shot (the carafes, the scale) is under the covered band. That’s fine for picture, which can run behind the interface. Text is different: put titles and on-screen text in the clear area. Studio’s export has no option to burn text into the video, so I’d add text in TikTok with the Text tool, inside the clear area.

Cut on the pauses so the voice stays in sync

When a video is cut into clips, by you or by a tool that splits it automatically, each cut also cuts the voice. If the cut lands on a word, the word gets chopped in half. To see how often that happens, I cut my narration twice: once every 10 seconds, and once at the nearest pause.

Two waveforms of the narration. Top: cuts every 10 seconds, at 10.00 and 20.00 seconds, land inside the words water and drip. Bottom: cuts at 8.75 and 19.29 seconds land in pauses of 0.69 and 0.46 seconds
Cuts every 10 s (red) land on words. Cuts at pauses (green) land in silence. Shaded areas are pauses of 0.3 s or longer.

Cut at 10.00 s

Starts mid-“water”

Cut at 8.75 s

Starts in a pause

CutLands onLevel at the cut
10.00 sthe middle of “water”−12.3 dBFS
20.00 sthe middle of “drip”−14.6 dBFS
8.75 sa 0.69 s pause−100 dBFS (silence)
19.29 sa 0.46 s pause−100 dBFS (silence)

Both fixed cuts landed mid-word, on speech louder than the narration’s average (−17.0 dBFS): play the first clip and it starts partway into “water”. Both pause cuts landed in digital silence. To keep cuts clean, write one sentence per shot, leave a short pause between them, and cut in the gap. If a tool splits the video for you, listen to each clip’s first and last word before you post.

Captions: let TikTok make them, then check them

TikTok captions uploaded videos automatically, and you can edit them (tap the caption, then Edit captions). TikTok’s help doesn’t mention importing a caption file, so keep your script open to correct any misheard words.

I also checked the SRT file Studio exported, since you’d upload one to YouTube with the same video. Each caption appeared 0.06 to 0.26 s before its first word (0.13 s on average). Three of the six were too long for two lines of 42 characters, a common subtitle limit used in Netflix’s style guide:

#Caption startsCharactersFits two lines?
10.14 s early40Yes
20.26 s early85No, by 1
30.07 s early86No, by 2
40.14 s early85No, by 1
50.06 s early59Yes
60.12 s early45Yes

The fix is in the script: keep each paragraph under about 84 characters, or split it in two.

Music: one sound per post

  • TikTok allows one sound per post, according to its editing help. If you want your own music bed under the voice, mix it into the file before you upload.
  • Mix it well under the voice. In our text-to-speech video test, a music bed at 15% volume measured −31.5 LUFS against −19.9 LUFS for the voice, about 11.6 dB under, and never covered a word.
  • Adding a TikTok sound later: the help says changing the music replaces “all previous background music and voices”. It doesn’t say whether that includes the audio inside an uploaded video, so try it on a draft before you post.
  • Business accounts can only use music that’s licensed for commercial use. TikTok recommends its Commercial Music Library for that.

Start from vertical footage

Landscape footage doesn’t convert cleanly to 9:16. When I exported a landscape project as portrait for the text-to-speech video guide, each clip was shrunk to fit, with black bars above and below. For this video I used only vertical clips, and five of the six filled the frame. The sixth, the woman with the cup, is slightly narrower than 9:16, and came out with a 34-pixel black bar on each side.

The same frame exported as landscape, filling the frame, and as portrait, where the landscape clip is shrunk to fit with black bars above and below
A landscape clip in a landscape export (left) and in a portrait export (right).

Uploading from a computer

You can upload on the web through TikTok Studio, at tiktok.com/tiktokstudio. The file has to be MP4 or WebM, 720×1280 or higher, up to 30 minutes and less than 10 GB. You can run a copyright check on the sounds before posting.

Two limits matter for voiceovers:

  • The web uploads the whole file. “To change the length of the video, upload your video in the TikTok app” (Making a post).
  • TikTok’s help documents no voiceover tool on the web. If you upload from a computer, put the voice in the file first (method 3).

Do you need to label an AI voiceover?

It depends on whose voice it sounds like. TikTok’s Community Guidelines say:

  • Generic AI narration: no label needed. Disclosure isn’t needed when “using generic text-to-speech (TTS) narration, when the TTS isn’t a recognizable voice of a known individual”.
  • A real person’s voice: label it. Disclosure is required when “AI-generated audio mimics the voice of a real person”. Disclosure means the AI-generated label, or “a clear caption, watermark, or sticker”.
  • Some uses aren’t allowed at all. For example, AI content that shows a public figure “supporting products… they haven’t actually addressed”. Humor and art, “such as a spoof, meme”, are allowed.

To label a video yourself before posting, tap Next, then More options, and turn on the AI-generated content setting. TikTok says that “won’t affect the distribution of your video” as long as it follows the guidelines (About AI-generated content).

TikTok can also add the label on its own, for example when you upload AI-generated content that has Content Credentials (C2PA) attached, and an automatic label can’t be removed. I searched my exported file for C2PA markers and found none.

One more rule applies whatever the voice: the guidelines make “reused or unoriginal content posted without creative edits” ineligible for the For You feed. So write your own script and make your own edit.

Troubleshooting

ProblemWhat to try
The voiceover has no soundTikTok’s checklist: the device isn’t on silent, the volume isn’t muted, sound is recording from the device’s native camera, earphones or Bluetooth work, and restart the app and device.
The voice disappeared after changing the musicExpected: changing the music replaces earlier background music and voices. Pick the sound first, then record the voiceover.
A saved sound is missing for a long videoSounds not available for long videos are hidden. TikTok says to set the video length to 15 s or 60 s on the recording page.
You can’t trim a video uploaded on the webThe web uploads the whole file. Trim it before uploading, or upload in the app.
You don’t see Voice or a voice effectTikTok’s help doesn’t cover this. Its creator-tools pages note that some features “may not be available in your region yet”. Check for an app update.

FAQ

Can I add a voiceover to a TikTok after posting?

TikTok’s help describes voiceover only while editing, before you post. What it does document: you can save a video to Drafts from the Post page and finish it later, and a deleted post stays in TikTok’s system for up to 30 days. To add a voice to a posted video, start from your own copy of the video, add the voiceover and post it again.

How do I do a voiceover on TikTok without my own voice?

Use TikTok’s text-to-speech (method 2), or make the narration with any AI voice, like the ones in our TikTok voice generator, and upload the finished video (method 3).

How do I add a voiceover to TikTok photos?

TikTok’s help doesn’t say whether Voice works on photo posts. If it isn’t there, make the photos into a vertical video with the voice in another editor, then upload it.

How do I talk over a sound on TikTok?

Add the sound first, then record your voiceover with Voice → Record. Changing the music afterwards replaces earlier voices.

Can I keep the original sound under my voiceover?

Older versions of the app had an “Original sound” toggle. TikTok’s current help doesn’t mention one. If you need control over the mix, make it in another editor and upload the result.

How many text-to-speech voices does TikTok have?

TikTok doesn’t publish a list, and third-party counts disagree.

Can other people use my TikTok AI voice?

No. TikTok says “only you can use your own AI generated voice”. You must be 18 or older to make one.

Can I add a voiceover to only part of a video?

TikTok’s help doesn’t cover this for in-app recording. In method 3 it’s simple: the voice only plays where you place it on the timeline.

For more on recording your own voice, see our voice-over recording guide and microphone picks. For apps that make voiceovers, see free voice-over software. To make a narrated vertical video like the one above, Lazybird Studio has the voices, stock footage and portrait export I used.

Keep reading

All articles →

Give your next video a voice

Natural, celebrity and character voices. Or clone your own.