TikTok voiceover tool

TikTok Text to Speech That Writes the Captions Too

Paste your script, pick a TikTok-style English voice, and download the MP3 with an SRT timed to the same take. Free, no watermark, and cleared for commercial use. The voices are our own, not TikTok's.

  • 31TikTok-style English voices
  • 18ready-made voice blends
  • 5free credits every month
0 bytes / 0 jobs / 0 credits

You can edit or delete these tags directly in your script.

Voice
SiennaEnglish (US) · Female
Advanced settings

Output

0.5x1x2x
Output format

Voice mix

The first voice sets pronunciation; the second only lends its character.

Primary voice

Sienna

Sets pronunciation and pacing.

Second voice

A fixed sample at your current mix and speed. No credits used.
  • Commercial use included on the free plan
  • No watermark on any output
  • Preview every voice without signing up

Voices for this page

TikTok voices to audition before you post

Energetic and promotional voices are listed first. Every card plays three sample lines, including a short hook, so you can hear how a voice opens a video before you spend a credit.

What you get

What this TikTok TTS voice generator gives you

A voiceover file you can drop into any editor, captions that came out of the same render, and nothing to buy before you post.

MP3 plus SRT in one pass

Every job returns the audio and a subtitle file cut at 42 characters a line, timed from the engine rather than guessed.

How the timing works

Standard English voices report the start and end of every word while they render. The subtitle cues are built from those timings, so a caption changes exactly when the word is spoken. Edit a line, render again, and the captions move with the audio. A WebVTT file comes along for editors that prefer it.

Hear every voice with its quality grade

Hooks, numbers, and pauses handled

On a paid plan, click Tidy up script: the AI pass adds breathing pauses to long lines and spells out symbols and units so nothing is skipped.

What the tidy pass changes

It only touches punctuation and adds three kinds of tags: a pause of up to five seconds, a slower read for a phrase that carries weight, and a pronunciation override for a brand name the engine would mangle. Every tag stays visible in your script and can be deleted with one click.

Reading something longer? Use the narrator page

Free means free to publish

No watermark, no attribution line, and commercial use on the free plan. Preview every voice without an account.

What the free plan includes

Five credits a month means five videos, and each one comes with room for 10,000 characters of English, far more than a short script needs. Renders stay downloadable for 72 hours. Nothing caps a single job either: a longer script simply adds a credit per extra block.

Need other languages? Open the main generator

Captions

TikTok captions that land on the right word

Burned-in captions carry most TikTok videos, and hand-timing them is the slow part. Here the caption track comes out of the same render as the voice.

  • SRT and WebVTT with every job, on the free plan included
  • Word-level timing on standard English voices, straight from the engine
  • Lines capped at 42 characters so they fit a vertical frame
  • Re-render after an edit and the cues move with the audio

One honest limit: word-level timing is a property of the standard English voices. Blending in a second voice changes nothing, because the second voice only lends its timbre and the timing still comes from the English primary. Import the SRT into your editor, CapCut or Premiere for example, and style the captions there.

Generate with captions
1
00:00:00,080 --> 00:00:01,900
Stop scrolling. Three seconds,

2
00:00:01,980 --> 00:00:04,300
one trick, and your edit is done.

3
00:00:04,420 --> 00:00:06,700
Here is exactly what to press.

Voice blends

Blend two voices into a TikTok AI voice of your own

A blend keeps the first voice's pronunciation and borrows the second voice's character. These starting points suit hooks, ads, and quick explainers; pick one in the generator's advanced settings and adjust the ratio.

Promo hook

Bright and quick, for openers and ads.

Sienna 50% + Brooke 50%

Product announcement

Short announcement read, lightly husky.

Delaney 30% + Quinn 70%

Ad read

Announcer weight with a throaty edge.

Delaney 50% + Walter 50%

Podcast host

Crisp and close, with husk underneath.

Delaney 30% + Maya 70%

Q&A explainer

Question-and-answer clarity, lightly husky.

Delaney 30% + Brooke 70%

Clean explainer

Brooke's character with Maya's accuracy.

Maya 10% + Brooke 90%

How voice blending works

The first voice decides how every word is pronounced and paced. The second voice contributes timbre only, at whatever percentage you set. Previewing costs nothing: the generator renders a fixed sample at your current mix and speed. When a blend works, save it as one of up to eight voices in this browser and reuse it for the next video.

How it works

How to make a TikTok voiceover from text

  1. A phone beside a speech bubble, standing in for a TikTok script.STEP 01

    Paste the script as you would say it

    Write for the ear: one idea per line, short sentences, the hook first. The generator shows the byte count and the exact credit cost before you submit.

  2. Three studio microphones of different sizes, one for each voice to compare.STEP 02

    Pick a voice and set the pace

    Play the sample hook on a few cards, choose one, and set the speed between 0.5 and 2 times. Blend a second voice if you want something in between.

  3. A clapperboard with sound waves, marking the download and edit step.STEP 03

    Download the MP3 and the SRT

    Both files land in My Speech when the job finishes. Drop them into your editor at the same start point, lower the music under the voice, and export.

Free plan, plainly

Free TikTok voice generator, and what a paid plan adds

Everything on this page works on the free plan. Paying buys speed and formats, not permission.

CapabilityFreeStarterCreator
PriceFree$6.99 a month, or $69.99 a year$15.99 a month, or $159.99 a year
Credits per month5 credits100 credits300 credits
Standard English characters per job10,000 for 1 credit10,000 for 1 credit10,000 for 1 credit
QueueFree queue, no promised timeSkips the free queueSkips the free queue
Output formatMP3MP3 and WAVMP3 and WAV
SubtitlesSRT and VTTSRT and VTTSRT and VTT
Script tidy (AI)Not availableIncludedIncluded
Premium voicesNot availableComing soonComing soon
Credit packsNot available100 credits for $5100 credits for $5
File retention72 hours30 days30 days
Commercial useIncludedIncludedIncluded
WatermarkNoneNoneNone
How credits are counted

One credit runs one job, and that job comes with room for 10,000 UTF-8 bytes: about 10,000 characters of English, or about 3,300 Chinese or Japanese characters. That is a whole article or a long script in a single go. Longer pieces are never turned away either, since each further block of 10,000 bytes adds a credit and what comes back is still one continuous file. Credits are reserved when you submit and refunded in full if a job fails.

Compare the plans

FAQ

TikTok TTS questions, answered

  • Does this use the real TikTok voices like Jessie or Ghostface?

    No. These are independent AI voices, not official TikTok voices such as Jessie or Ghostface. You get a lively TikTok-style voiceover you own outright, but not a copy of those named voices.

  • How do I add the voiceover to my TikTok video?

    Download the MP3, import it into your editor alongside the footage, and place it at the start of the clip. Lower the music while the voice speaks, export, then upload to TikTok as usual.

  • Can I get captions that match the audio?

    Yes. Leave subtitles on before generating and the SRT and VTT download with the audio. Standard English voices give word-level timing, so each caption changes on the word being spoken.

  • What is the best speed for a TikTok voiceover?

    Start at 1.0 and listen to your own script. Nudge up to 1.1 or 1.2 only if every word stays clear; a shorter script usually beats a faster read.

  • Is there a watermark on the audio?

    No. Downloads carry no watermark and no spoken tag on any plan, including free. Captions come as a separate file, so their look is entirely up to your editor.

  • How long can a TikTok voiceover be?

    As long as your credits allow. One credit runs one job with room for 10,000 characters of English, more than a short video will ever need. The generator shows the exact cost before you submit, and the audio length appears in your editor.

  • Can I use the same voice across all my videos?

    Yes. Your last chosen voice is remembered on your account, and you can save up to eight voices, blends and speed included, in this browser. Pick the saved voice and the delivery matches the last video.

Make your TikTok voiceover now

Pick a voice, check the credit cost, and download the MP3 with captions.