Text to speech generator

Free Text to Speech With Subtitles and No Character Limit

Paste a script, pick a voice or blend two into your own and get an MP3 with subtitles timed to the same render. One credit makes up to 10 minutes of audio, with commercial use and no watermark.

0 bytes · 0 credits

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

Voice
MayaEnglish (US) · Female
Make your own voice

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

Primary voice

Maya

Sets pronunciation and pacing.

Second voice

A fixed sample at your current mix and speed. No credits used.
Advanced settings

Output

0.5x1x2x
Output format
  • Commercial use included on the free plan
  • No watermark on any output
  • Blend and preview voices without signing up

Free text to speech plan

One credit sounds small. It isn't.

One credit makes up to 10 minutes of audio with subtitles. That is a full YouTube video, a story chapter or a course lesson.

Unlimited commercial use

Publish what you generate on YouTube, TikTok, a client project or a paid course. No attribution line, no watermark, no separate license to buy.

Subtitles in every render

SRT and WebVTT written from the synthesis timeline, so cue boundaries land on real pauses instead of guessed intervals.

Long scripts in one job

A full video script or a short chapter goes through as a single render, which keeps one voice and one pace across the whole thing.

Audition before you spend

Every voice carries three sample lines you can play before you spend a credit. Listening costs nothing and needs no account.

Make your own voice

Blend any two voices into one that is yours.

Server-side rendering

Generation runs on our machines, so a phone gets the same output as a desktop and long jobs survive closing the tab.

Voice mix

Create your own AI voice

Pick two voices, set the mix and make it yours.

  • 54 voices to mix, across languages
  • 35 ready-made blends to start from
  • Free previews, no sign-up
  • Save it under your own name
Create your voice

Hear our blends

Warm narrator

Male warmth with Maya's clean pronunciation.

Maya 30% + Walter 70%

Promo hook

Bright and quick, for openers and ads.

Sienna 50% + Brooke 50%

British-toned Mandarin

Mandarin pronunciation, British lesson timbre.

Ruoxi 10% + Freya 90%

Premium voices

Voices that act out your script

1,600+ expressive voices that laugh, sigh and pause on cue, in 40 languages. Paste a script of any length and get one MP3 with captions.

  • 1,600+ voices in 40 languages
  • Emotion tags like <laugh> and <sigh>
  • One MP3 for a script of any length
  • SRT and VTT captions included
Explore premium voices

Audio and captions

Text to speech that writes the subtitle file too

Most generators hand back an audio file and leave the timing to you. Here the caption track comes out of the same render, so the two never drift apart.

  • SRT and WebVTT from every job, on the free plan included
  • Timing taken from the engine rather than estimated
  • Short cue lines that read easily on a phone screen
  • Edit a line, render again and the captions move with the audio

Cue timing comes from the render itself, so every caption lines up with the voice. Each job produces SRT and VTT files that stay in sync with the audio.

Generate with subtitles
1
00:00:00,120 --> 00:00:03,480
Stop scrolling. This one trick

2
00:00:03,600 --> 00:00:07,020
just saved me three hours of editing,

3
00:00:07,340 --> 00:00:09,900
and it takes ten seconds.

Voice library

An AI voice generator you audition by ear

Choose a voice by the kind of script you write. Available previews cover calm narration, an energetic hook and a conversational story. Or blend two into your own.

Browse all voices
Lucia (Spanish)Spanish, Natural
More voices

Use cases

Who turns text to audio every day

An upright phone displays a play button and ruled caption lines.

Short video

A script goes in, the voice track and captions come out sized for a vertical timeline.

MP3 with SRT and VTT

Sound waves rise from the pages of an open book.

Long-form narration

Documentaries, courses and audiobooks in one steady voice.

Up to 10 minutes per credit

Sound waves flank a globe to represent spoken content in different languages.

Language content

Japanese, Chinese, Spanish, Hindi and more, with captions.

9 languages on the free plan

Over-ear headphones sit beside a document with ruled lines.

Accessibility

Turn an article or a manual into audio people can listen to instead of read.

Downloadable, no player required

How it works

Three steps through the text to speech generator

  1. A hand feeds a written script into an audio conversion machine.STEP 01

    Paste your script

    Paste your full script, however long. One credit makes up to 10 minutes of audio.

  2. A studio microphone emits sound waves beside an adjustment dial.STEP 02

    Pick a voice or make your own

    Play the samples, set the speed or blend two voices into your own.

  3. A download arrow points to a film reel and a strip of captioned frames.STEP 03

    Download the audio and captions

    Take the MP3 with the SRT and VTT files, ready for any video editor.

Free plan, plainly

Text to voice free, and what a paid plan adds

One credit makes up to 10 minutes of audio. Free gives you five a month. On Starter, a 10-minute voiceover costs 7 cents.

CapabilityFreeStarterMost PopularCreator
Premium voices Try AI voice over
Not included
1,600+ expressive voices in 40 languages1 credit per 400 bytes
1,600+ expressive voices in 40 languages1 credit per 400 bytes
Plan and credits
Price
Free
$6.99 a month, or $69.99 a year
$15.99 a month, or $159.99 a year
Credits per month
5 credits
100 credits
300 credits
Audio per month
Up to 50 minutes
Up to 1,000 minutes
Up to 3,000 minutes
Text per credit, standard voices
10,000 bytes
10,000 bytes
10,000 bytes
Text per render
No limit
No limit
No limit
Credit packs
Not available
100 credits for $5 that never expire
100 credits for $5 that never expire
Voices
Voices
50+ voices in 9 languages
50+ voices in 9 languages
50+ voices in 9 languages
Custom voices
Blend any two of 50+ voices
Blend any two of 50+ voices
Blend any two of 50+ voices
Blend control
Set the mix in 10% steps
Set the mix in 10% steps
Set the mix in 10% steps
Cross-language blends
Included
Included
Included
Script editing
Speed
0.5x to 2x
0.5x to 2x
0.5x to 2x
Pauses and slow down
Add pauses up to 5 seconds, slow any phrase
Add pauses up to 5 seconds, slow any phrase
Add pauses up to 5 seconds, slow any phrase
Pronunciation
Set how any word is read
Set how any word is read
Set how any word is read
Script tidy (AI)
Not available
Included
Included
Files and rights
Subtitles
SRT and VTT
SRT and VTT
SRT and VTT
Output format
MP3
MP3 and WAV
MP3 and WAV
Queue
Free queue, no promised time
Skips the free queue
Skips the free queue
Renders at once
1
Several
Several
File retention
72 hours
30 days
30 days
Watermark
None
None
None
Commercial use
Included
Included
Included

Minutes per credit are based on standard voices reading English at normal speed.

How credits are counted

Each credit covers 10,000 bytes of text with standard voices and makes up to 10 minutes of audio. With premium voices, each credit covers 400 bytes. Letters in English and most European languages take one byte each, while characters in scripts such as Chinese, Japanese or Hindi take three. Credits are refunded in full if a job fails.

See plans and pricing

Languages

Text to speech in nine languages, free

Every plan covers all nine, with subtitles and commercial use included.

  • English (US)
  • English (UK)
  • Japanese
  • Chinese (Mandarin)
  • Spanish
  • French
  • Hindi
  • Italian
  • Portuguese

FAQ

Text to speech questions people ask first

  • What is text to speech, and what does this one do?

    Text to speech turns written text into spoken audio using a synthetic voice. This one also returns a subtitle file timed to the audio it just produced, so you can caption a video without lining the cues up by hand.

  • Is TTSLark text to speech free to use?

    Yes. Five free credits every month, each one up to 10 minutes of audio with subtitles. Commercial use included, no card, no watermark.

  • Can I use the audio in YouTube or TikTok videos commercially?

    Yes, on every plan including the free one. Everything you render carries a commercial license, and nothing you publish needs to credit us.

  • Can I download the subtitles with the audio?

    Every job returns SRT and WebVTT alongside the MP3, timed from the same render, so the captions line up with the voice.

  • Can I create my own AI voice?

    Yes. Blend any two voices, set the mix and save it under your own name. No recording needed, and previews are free.

  • What is the character limit per generation?

    There is no fixed character limit. Each credit covers 10,000 bytes of text, and every further 10,000 bytes adds one credit, so a long script runs in a single pass. The generator shows the byte count and the credit cost before you start.

  • Does my first render get priority?

    Yes. Your first render gets priority, and paid plans get priority on every render.

  • Which languages are supported?

    Nine languages on every plan, the free one included: US and UK English, Japanese, Mandarin Chinese, Spanish, French, Hindi, Italian and Portuguese.

Turn your script into a finished voiceover with subtitles

Other AI voice tools give you enough free credits to test them. We give you enough to finish the video.

Start freeSee pricing